Pith. sign in

Paper Citation Record · LEDGER

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret

As of 11 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 0 inbound Pith citation observations for arXiv:2412.20824.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.20824 v2

Coverage vector

measured 95 of 95 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T23:21:24.235396Z

measured 95 of 95 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

95 of 95 outbound references displayed

  • verified exact5
  • verified fuzzy54
  • unresolved35
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c79b37b1-efbe-47a6-8530-5e2605e069db · outbound

This paper cites write newline.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.744389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.744389Z digest=sha256:5e98d4fa3657faac178fab91d4eaa52df43ede29394498e22e72dcfa673ec6ac

Observation 90ea351d-efce-4427-bb00-69d4654bcef2 · outbound

This paper cites and Lazaric, A.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Lazaric, A

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.750901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.750901Z digest=sha256:f44a6c9a530cd3fe0bd60d276e51c2d9076375b2074f3a4dfecc422978f54ad4

Observation fd091a31-2653-4c37-9b5c-d42c43b95f49 · outbound

This paper cites and Jia, R.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Jia, R

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.756995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.756995Z digest=sha256:467b64df62d4468f438fa026a9c3a36f235bef4db2a6bdc6d4466867192d8127

Observation 24a80688-532c-4d7c-93fc-9dfbda12c098 · outbound

This paper cites Langevin soft actor-critic: Efficient exploration through uncertainty-driven critic learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Langevin soft actor-critic: Efficient exploration through uncertainty-driven critic learning

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.762926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.762926Z digest=sha256:02dae93339f63a98573c6b16df4343e535b1a8b8e66b9be96f917da8e5a0f7d9

Observation bf88aff9-8a63-4336-9762-f41a1d4035ff · outbound

This paper cites G., Osband, I., and Munos, R.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret G., Osband, I., and Munos, R

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.768433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.768433Z digest=sha256:766f4eb35508ec6163ccc1d8d5acf9b9ffe92dfd8d1e6e5115b471a2093fc82a

Observation 47f0204f-7f69-4413-947c-e1e467ba31e7 · outbound

This paper cites Analysis and geometry of Markov diffusion operators, volume 103.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Analysis and geometry of Markov diffusion operators, volume 103

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.774128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.774128Z digest=sha256:a3a52ab77b6c4eb8eca3766df783a7e45583cb54fbea4663a0e0297dc6732689

Observation 8a6a16c3-0093-47ce-8ca1-f56d3985394c · outbound

This paper cites and Kolesnikov, A.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Kolesnikov, A

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.779403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.779403Z digest=sha256:4b5dd6a6a4a81e792134f942a4475e7ab4fb7291c346ebe1c03cbf06753eca95

Observation ce438d60-247f-43fa-b75d-2974c3a14d69 · outbound

This paper cites G., Sutton, R.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret G., Sutton, R

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.785067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.785067Z digest=sha256:3d0d561690aed42b1bd03715282ee123366d1e1b426950a0e225975e46d9066c

Observation 32c79215-61a8-442b-8033-fa7e2bef0e25 · outbound

This paper cites On the log-sobolev constant of log-concave measures, 2023.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret On the log-sobolev constant of log-concave measures, 2023

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.790140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.790140Z digest=sha256:9b90aae27e8fdd2c5771d55548d4a7fea28cf899d4870c19fe006ec0cc11b73d

Observation e2a4f894-c078-4733-9860-923742b4e3cb · outbound

This paper cites Concentration inequalities.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Concentration inequalities

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.795199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.795199Z digest=sha256:878858fda226ba4a746d7d47d03cd7aab8ef488325121d6ddfd69a7304cd10e2

Observation c1826ee4-19be-4ad9-b539-aad525d09244 · outbound

This paper cites J., Leary, C., Maclaurin, D., Necula, G., Paszke, A., Vander P las, J., Wanderman- M ilne, S., and Zhang, Q.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret J., Leary, C., Maclaurin, D., Necula, G., Paszke, A., Vander P las, J., Wanderman- M ilne, S., and Zhang, Q

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.799825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.799825Z digest=sha256:5ac1a6aecb66daed0ef479d4b1bc1f331cf150e6b6fe5cc1db552a68baf64f03

Observation 52a1fc56-909b-4d84-9bbc-6165d3806bd0 · outbound

This paper cites K., Dimitrakakis, C., Eriksson, H., Grover, D., and Jorge, E.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret K., Dimitrakakis, C., Eriksson, H., Grover, D., and Jorge, E

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.805167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.805167Z digest=sha256:22eec2bdd05cdbdc69c6d5fe123811a75afe293bd810c2ddfb9b34ec2a813f61

Observation d6e64e47-0d7b-4b22-88c9-e6df2a2fd889 · outbound

This paper cites Bayesian linear regression with sparse priors.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Bayesian linear regression with sparse priors

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.810610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.810610Z digest=sha256:c5a4ebfbbe48396d9d9bbc4e32e694ddca5ba28883c526d11f8ca9a8ce5fae58

Observation 66f624fc-41d8-4459-a2cc-1a234e1461d9 · outbound

This paper cites A note on talagrand’s transportation inequality and logarithmic sobolev inequality.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret A note on talagrand’s transportation inequality and logarithmic sobolev inequality

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.815060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.815060Z digest=sha256:d012c7c4ca43a4c2e683e3bf4f7ebd42cb4d9b78877e0ee464eb6d01be0ed2d5

Observation 39d24002-b1da-4042-9a1f-9ce048bc7a19 · outbound

This paper cites and Lehec, J.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Lehec, J

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.820231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.820231Z digest=sha256:e3236d619e0143763f934a38f2bcbf8ec198a4fe330f2086cef64ea59d4b6336

Observation 82221f32-0d3a-43ea-a5db-3bafdfe99385 · outbound

This paper cites Thompson sampling for high-dimensional sparse linear contextual bandits.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Thompson sampling for high-dimensional sparse linear contextual bandits

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.825232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.825232Z digest=sha256:d83fdbcd8506b4f81031828f97dbd79965a4d6cf1341e2128e71df676b39f48b

Observation 495a6887-1319-43af-a4af-6e0af5a84f6d · outbound

This paper cites Dimension-free log-sobolev inequalities for mixture distributions.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Dimension-free log-sobolev inequalities for mixture distributions

Reference 17

Resolution
metadata mismatch
raw_fallback, observed 2026-08-10T23:21:25.032899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.829877Z digest=sha256:fbd7ca06fd63523912b195474dcc62bfc63238cce7e9ee5c00f7c8b6128924e6

Observation 17879cc5-8ad0-4ac6-b268-f245c33a8351 · outbound

This paper cites an unresolved cited work.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-10T23:21:26.118917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.835023Z digest=sha256:e5f58c926872c247e8022567a8690f9f29db6e6080f13499ce452155fb83b24a

Observation 43cef370-880a-4a21-8bb1-f63e347fc822 · outbound

This paper cites R., Gopalan, A., and Maillard, O.-A.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret R., Gopalan, A., and Maillard, O.-A

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:26.104243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.840819Z digest=sha256:472e8923dcf25a66a362c7f5507dd2f37d299b09a73761029d722b52486d52aa

Observation 145afcf2-207b-48b0-bf4b-aaf42c13b51a · outbound

This paper cites Deep reinforcement learning in a handful of trials using probabilistic dynamics models.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Deep reinforcement learning in a handful of trials using probabilistic dynamics models

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:26.089066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.845410Z digest=sha256:a6d62ca5feb4a5722035dd5593e512128dc491c0043add6024b9bacd4f3262e2

Observation 82493d28-bb77-4942-8fac-83122740241c · outbound

This paper cites Bagger: A bayesian algorithm for safe and query-efficient imitation learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Bagger: A bayesian algorithm for safe and query-efficient imitation learning

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:26.073468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.850468Z digest=sha256:e7387b0688b0e1e934a80a2950d5255a12a32ec70d49a183329aa418b59adee0

Observation f55647a2-cd2d-4074-a61d-00bf3a71b7bf · outbound

This paper cites Model based B ayesian exploration.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Model based B ayesian exploration

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:26.056688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.855466Z digest=sha256:d4ca3b17536c1bb9d069066fc99a74e305f4d83634e4b7350e3691a5d983f78f

Observation dbdce769-4c17-4802-8735-d243075fee2a · outbound

This paper cites Robust Bayesian reinforcement learning through tight lower bounds.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Robust Bayesian reinforcement learning through tight lower bounds

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:26.040655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.860694Z digest=sha256:1c4e9659e9ad7155e7f9be44971ec3e4cc6cb3b4fd179b11bf93648fc5cb8230

Observation 19fb77e6-8b6a-4d22-91f2-af3472c6f9ac · outbound

This paper cites A., J Reddi, S., Williamson, S.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret A., J Reddi, S., Williamson, S

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:26.024151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.865056Z digest=sha256:361592c091a59fbe259f04516387b2180a2860794d2249f686318bc9adeb3bfd

Observation dc78b60a-a0cf-4efa-bc40-bc39246a3d27 · outbound

This paper cites Langevin DQN.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Langevin DQN

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.870361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.870361Z digest=sha256:ee57c7fa6472b598638fbbb65361707e19360cb808635f62bb4472ca1020eda5

Observation 233b60f1-f61b-4d0d-bbb1-390601940ecf · outbound

This paper cites Exponential families in theory and practice.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Exponential families in theory and practice

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:26.006703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.875612Z digest=sha256:fdb2eb90d191d45ce6901bb4ac2fa4cf996f5c929df1f63121e94e6b9b9e747b

Observation 0569a81b-c00d-4ae8-9de7-8cdc48614312 · outbound

This paper cites Sentinel: taming uncertainty with ensemble based distributional reinforcement learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Sentinel: taming uncertainty with ensemble based distributional reinforcement learning

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.990337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.880167Z digest=sha256:46fd30c1edbc8e9b50585ce18add194188a49331a2957e38366124e0709241dc

Observation 20608f2c-d801-459c-9230-6343eaa1fcc1 · outbound

This paper cites and Ming, Y.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Ming, Y

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.974067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.885482Z digest=sha256:d0eb85fcd9c81c81dba574130a996f15af094f911d6158b7f9ab0aefba69138d

Observation 707567aa-3a36-4941-820c-a901a2ccee92 · outbound

This paper cites Bayesian bellman operators.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Bayesian bellman operators

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.959071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.890608Z digest=sha256:f602c41e7f595c44804cdd9e6b665d7fc61c41419de721739481dc84becfe571

Observation def80249-cb26-475a-a436-4cb3cb61579b · outbound

This paper cites an unresolved cited work.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-10T23:21:25.943808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.895236Z digest=sha256:fd87084fafe68701138f15bf3baa6da9eb0e483ed0fc0884b8bde7e6819c55f4

Observation 6ad7fa1e-a26a-41d5-9d2e-37b2a61c546c · outbound

This paper cites Addressing function approximation error in actor-critic methods.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Addressing function approximation error in actor-critic methods

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.899900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.899900Z digest=sha256:987850627bb881eca8188bf435c3a14492a4aaf9fe18a80b2df5d22b2e9a4b4f

Observation b6403cb3-cdb7-4234-800c-94874086cac1 · outbound

This paper cites J., Tellex, S., Chowdhary, G., Roy, N., and How, J.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret J., Tellex, S., Chowdhary, G., Roy, N., and How, J

Reference 32

Resolution
verified exact
doi, observed 2026-08-10T23:21:24.287131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.905379Z digest=sha256:59f2fac304f66b16a0d4592d28724264618ce4e894f46cc3541368d2870ec44b

Observation c1c3d98f-ced7-4b40-8d1e-f0d9a1bce075 · outbound

This paper cites Convex optimization: Algorithms and complexity.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Convex optimization: Algorithms and complexity

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.911033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.911033Z digest=sha256:dc6a1ba19178aee986a3bbacaf163c6b051df058a0d67a61425b679948d0980c

Observation a126eb85-b5f0-4071-8419-bdf984e69e78 · outbound

This paper cites A review of consistency and convergence of posterior distribution.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret A review of consistency and convergence of posterior distribution

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.919586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.915848Z digest=sha256:4a54db8f1578a20333ca9593e53f24e7376c5ed28e0b4b2780a3a987aa8ffdf8

Observation 107bf671-3da3-433b-a72b-1a1fe5af4458 · outbound

This paper cites Bayesian reinforcement learning via deep, sparse sampling.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Bayesian reinforcement learning via deep, sparse sampling

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.904403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.920665Z digest=sha256:0a8e86ec17055b1b8a886e3bb78917cf8f9d0baf55fce26cb6494001caf30e56

Observation 0edfe199-5126-4de9-82a4-a7af01f66330 · outbound

This paper cites A PAC-Bayesian Link Between Generalisation and Flat Minima.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret A PAC-Bayesian Link Between Generalisation and Flat Minima

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.926649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.926649Z digest=sha256:0c49cacbca5053a2980d2c942e39bb7ce0966d2ba735e7f1fdb7b8b2002c5631

Observation adeeafca-67b9-42df-8194-bf72da36e669 · outbound

This paper cites R., Precup, D., and Xu, P.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret R., Precup, D., and Xu, P

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.888984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.931671Z digest=sha256:b8dae05df06e454d130a82fd2133a35ca65f2860ab93093b18bc22eb3a9ba681

Observation f6ad0d8a-a910-4967-81d5-d50d9b33f1ed · outbound

This paper cites and Stroock, D.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Stroock, D

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.873630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.936543Z digest=sha256:d07b58881e64a3fac07e74b7aa287f2848435d1c3209240d8e775600ce33bb3e

Observation c5accb49-01b4-4cf7-bc82-cdcd1bcdb2fa · outbound

This paper cites Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.942519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.942519Z digest=sha256:df162d1f9f215b8880dcf9ccc18a2f516fad967aae5b59297d648d00674dbe60

Observation f6fdbf9f-4875-424d-8358-79dde2b12e76 · outbound

This paper cites an unresolved cited work.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-10T23:21:25.856656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.948115Z digest=sha256:e0428f3fd942b705879292dcc24d888078181778fd5d9f56076a45dfabdd46ac

Observation cad046ef-bdcc-4552-b5a5-5bae774b49c5 · outbound

This paper cites Optimal regret is achievable with bounded approximate inference error: An enhanced bayesian upper confidence bound framework.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Optimal regret is achievable with bounded approximate inference error: An enhanced bayesian upper confidence bound framework

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.841099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.953111Z digest=sha256:6cbd432a9db11a539c0ede9525c8c3f2768ff0206cbf5c7d9a490b25fc764cf7

Observation 32f1ea9c-15c5-4336-8923-cdd4c7c90151 · outbound

This paper cites Tight regret and complexity bounds for thompson sampling via langevin monte carlo.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Tight regret and complexity bounds for thompson sampling via langevin monte carlo

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.825330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.959610Z digest=sha256:e678627e0b6a99dddde940e21c5591df172739b8e00be7460761595779e83027

Observation b668ccec-841a-40d9-bf7d-af50ff59a5ae · outbound

This paper cites R., Precup, D., Anandkumar, A., and Azizzadenesheli, K.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret R., Precup, D., Anandkumar, A., and Azizzadenesheli, K

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.809590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.964984Z digest=sha256:d5faf29bab16139f28910af89be5ecb4e2d8a2f485b344bcf3f4a8b0af3bafc4

Observation 146ff183-68b5-4b2a-aa2b-6a8d60db0ad3 · outbound

This paper cites A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.970314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.970314Z digest=sha256:cac1285930f6436ce02f8ee080aaa61aca2e14453055afff2783cb1f73b9fc0c

Observation ef9d697e-befa-4df4-9df0-155f64ec722a · outbound

This paper cites I Can't Believe It's Not Better!.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret I Can't Believe It's Not Better!

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.794381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.975781Z digest=sha256:0db9d23b6683d9237c91a2b93f56039a5c2f1c53d95ecd1de91046e4ac8be874

Observation 12e55d4c-fb13-455f-adaf-87249d7afe1e · outbound

This paper cites an unresolved cited work.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:23.981685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:23.981685Z digest=sha256:075308768afee4162ec559a46cbb010989043cc811795dc1bf1d03b48985d893

Observation 65cc44a3-085a-46ff-b01f-1634d80188e9 · outbound

This paper cites L., Ma, Y., and Mitra, S.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret L., Ma, Y., and Mitra, S

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.769434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.986328Z digest=sha256:d91e2bef88366c7d43847bb06176ddf54ec781dfb685ff2f2f08532cd1061a15

Observation 1ad1c753-7d6a-4f31-98df-ffd962cbe965 · outbound

This paper cites Learning linear-quadratic regulators via thompson sampling with preconditioned langevin dynamics, 2023.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Learning linear-quadratic regulators via thompson sampling with preconditioned langevin dynamics, 2023

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.754385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.992244Z digest=sha256:12097ccd6bbac62026b7832728277a135eac433fc6ee7761817613269b2db42f

Observation 1c9caac6-c639-432e-946d-6312a8a2bdec · outbound

This paper cites Approximate Thompson Sampling for Learning Linear Quadratic Regulators with $O(\sqrt{T})$ Regret.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Approximate Thompson Sampling for Learning Linear Quadratic Regulators with $O(\sqrt{T})$ Regret

Reference 49

Resolution
verified exact
local_arxiv, observed 2026-08-10T23:21:24.726750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:23.997359Z digest=sha256:6a260aa0aa139456cc6a1f2e1287c50ae4c3b9ae4a623d66417f951fa46ce306

Observation 83c53a03-c04b-42f0-8f02-a01a3db2f89e · outbound

This paper cites and Suzuki, T.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Suzuki, T

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.736933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.004720Z digest=sha256:4e0569f2851d669e9f2c3d878b93fce9296d750fae11f0abff99e7bf7b7b0986

Observation b753f753-9b3f-4f31-a6d0-4745286736cd · outbound

This paper cites and Vuong, T.-D.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Vuong, T.-D

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.721643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.010185Z digest=sha256:d409615f511557a40cbcde90b67fbaf10d867214cfcc7ab5cb56e3f2cc78384f

Observation 28579f40-badc-4449-8316-56ae9a7d8da2 · outbound

This paper cites Statistical efficiency of score matching: The view from isoperimetry.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Statistical efficiency of score matching: The view from isoperimetry

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.706202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.015379Z digest=sha256:57a19ef37207e4bbed455ca4fd74833b68da17ace17cacb6f4faf4ba7e03edc0

Observation 91e5583c-55a2-499e-be23-2760f4cd570c · outbound

This paper cites and Yin, G.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Yin, G

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.690763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.021408Z digest=sha256:e93ef7aad7844097fc0eae2e7e45eb0fc9b01c6946fe5c97d64a3586652afe0d

Observation 73a71098-ab16-4185-9472-979fbfc29f8f · outbound

This paper cites L., Yin, M., Wang, M., Wang, Y.-X., and Ma, Y.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret L., Yin, M., Wang, M., Wang, Y.-X., and Ma, Y

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.675420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.026210Z digest=sha256:d40a06efd9590637c544b0819f86002e6cd9085fb53e4cf2a6ef7a6c2b5cbdce

Observation 8a322473-5f75-4c8c-8742-423250f3d739 · outbound

This paper cites and Szepesv \'a ri, C.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Szepesv \'a ri, C

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:24.031192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:24.031192Z digest=sha256:687b8523209035ecd896e75e338bc92337da7fd6cf9a64bab43d583dd076bc13

Observation cae18ede-9ae9-4d98-9178-d6b922bf466d · outbound

This paper cites Concentration of measure and logarithmic sobolev inequalities.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Concentration of measure and logarithmic sobolev inequalities

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.649684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.036214Z digest=sha256:918782154b3889c63501b35d3f1421fcec8aca7bfbff13ad7c11600bd546ff81

Observation 1da38ed7-2be4-4504-b548-5fa0a1b5546c · outbound

This paper cites E., Bottero, A.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret E., Bottero, A

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.634148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.040955Z digest=sha256:1bf8d206fb73fd75b13777a1eaa261502eb2770ca2c7f893f7b8b4b81d419846

Observation 4162fbac-612d-4c75-a9ce-5fee7308fa14 · outbound

This paper cites E., Bottero, A.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret E., Bottero, A

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.618336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.046381Z digest=sha256:9e9b16f93be810a4b08d3e84f5dafd2a8bcbda3c274f1fb9ff0e10f16cafe8fb

Observation 9c30ffe4-ce24-4a51-8d53-d58e69323d31 · outbound

This paper cites Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization

Reference 59

Resolution
verified exact
local_arxiv, observed 2026-08-10T23:21:24.702595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.051213Z digest=sha256:0167f35f8215dccbf57b03cf8919c3f411d5948904925901a74ca7ae9a6b0110

Observation 6397ae1e-6598-46da-91d7-967c9ba33ffc · outbound

This paper cites On approximate thompson sampling with langevin algorithms.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret On approximate thompson sampling with langevin algorithms

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.602908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.056910Z digest=sha256:c9afd9d3df8730047f2b55f29e6d02feff98c711431593bb6b14c5342eb82cb3

Observation a68f8364-9790-4cd5-a6f5-689665a3abe5 · outbound

This paper cites Bayesian linear regression.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Bayesian linear regression

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:24.061381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:24.061381Z digest=sha256:42e6a16fafdba348aa26992c3571dad9dcafc4b3706673f9a4c7a64130a95d6a

Observation 52cf9a73-1abc-4778-884b-81e679bad9fb · outbound

This paper cites S., and Aggarwal, V.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret S., and Aggarwal, V

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.576928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.065792Z digest=sha256:349f785a63d6fcca6233cbc6b4b183881682074116b6f87d16f7cd2685e152c0

Observation 912e96b7-6941-402d-9eff-b443ff17d278 · outbound

This paper cites A diffusion process perspective on posterior contraction rates for parameters.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret A diffusion process perspective on posterior contraction rates for parameters

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.561995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.070796Z digest=sha256:bdfe5748fa4b8b29962e5c813c3a70a519b4686783c1f52fe32b0a9d57b48ffb

Observation 91488b25-3b00-4d69-ad9f-8b83d52492bf · outbound

This paper cites Posterior sampling via langevin monte carlo for offline reinforcement learning, 2024.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Posterior sampling via langevin monte carlo for offline reinforcement learning, 2024

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.545714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.075307Z digest=sha256:65505f80fbcae4ae13b9b8f1bad3be424258a399b28853d0a8192e9a20e81496

Observation a8a63be7-1c06-441f-ba95-183bfd24f606 · outbound

This paper cites Convex analysis of the mean field langevin dynamics.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Convex analysis of the mean field langevin dynamics

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.530511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.080891Z digest=sha256:bbf0268acc6082ba4bb3f3e9d3fbfa3907587b35ea41a349876c654c71a15e64

Observation e5099466-59f2-4886-93cb-22227bdfb95e · outbound

This paper cites Variational bayesian reinforcement learning with regret bounds.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Variational bayesian reinforcement learning with regret bounds

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.515426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.085347Z digest=sha256:af9305e32a7baf298a854bb4935904e5f649c51965c43b31932bdb24029ce4b8

Observation bf6bbef4-3b77-45f9-8d66-7399ea2f6249 · outbound

This paper cites The uncertainty bellman equation and exploration.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret The uncertainty bellman equation and exploration

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.498575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.090634Z digest=sha256:ca58b0eabc95f0d19c11ef24af8edfa8e715e0aee17e31305b5958710c0f570e

Observation d582f12f-f343-41d3-807f-3acb4550c0b7 · outbound

This paper cites and Van Roy, B.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Van Roy, B

Reference 68

Resolution
verified exact
raw_fallback, observed 2026-08-10T23:21:24.677543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.095264Z digest=sha256:2307e0e63d63a397a0138818d5f04c4098ef164a28504b7d9e01ea44f0a82b81

Observation 0b1b5790-a9d3-4157-818e-69d014156f58 · outbound

This paper cites and Van Roy, B.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Van Roy, B

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.481516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.100012Z digest=sha256:34049a14edbbcfb70c200e9bb0df2eb454ee0726c91aaa0c9eef76400996a1d7

Observation 5d408a8f-b347-4bfa-a509-6239aa12bc59 · outbound

This paper cites an unresolved cited work.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Unresolved cited work

Reference 70

Resolution
unresolved
raw_fallback, observed 2026-08-10T23:21:25.465731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.104582Z digest=sha256:4c077c26754934cde76bb038f17a9f32e795e09849b614941fd9f103494e947c

Observation adb61100-055d-4ed6-9caf-c3948676dfc0 · outbound

This paper cites (more) efficient reinforcement learning via posterior sampling.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret (more) efficient reinforcement learning via posterior sampling

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.449620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.109375Z digest=sha256:de1548992fbacf73730f018c0f3bc77983acb5b03a172058e9946af2a33fb6b2

Observation d50b6341-a56c-4766-b725-d6262a0e64b2 · outbound

This paper cites M., Dwaracherla, V., Ibrahimi, M., Lu, X., and Van Roy, B.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret M., Dwaracherla, V., Ibrahimi, M., Lu, X., and Van Roy, B

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.433505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.113859Z digest=sha256:9ad98fa1c8b3f168ad49a22d969c467dd5c730c1c7b5bd8e60ee86356a4ed87c

Observation b688bc4f-65a2-4490-90a1-e9a70578e94b · outbound

This paper cites Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning

Reference 73

Resolution
verified exact
local_arxiv, observed 2026-08-10T23:21:24.577601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.119264Z digest=sha256:b35c99eac237390241cf6c357b7f5cda05900f0a61b2ae8d2b0e20148e5d7852

Observation a91e9e13-f817-4feb-b1e8-c73bdd5dcfb0 · outbound

This paper cites Thompson sampling and approximate inference.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Thompson sampling and approximate inference

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.417206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.124503Z digest=sha256:2c47f3ce74f9f3e8aa96f61cbaca2e6e22d0d3a0c2351722765b7756813115fe

Observation a96770fb-a3ab-4523-81dc-27f308e234d6 · outbound

This paper cites Sample-efficient cross-entropy method for real-time planning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Sample-efficient cross-entropy method for real-time planning

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.401254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.129425Z digest=sha256:c469eac9f92c1817ee813fa19ae2727d6e670f5d36af7405ea90af50e6e018a3

Observation 1e92ae7c-9ac7-4c58-8902-23f4b3985910 · outbound

This paper cites Online kernel selection for bayesian reinforcement learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Online kernel selection for bayesian reinforcement learning

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.385924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.134429Z digest=sha256:4d16bb772a25fdbbb6bf010bd55a3034ed9a51467a672d4583e0f9e5a435ccd9

Observation 01c34756-842b-40d2-8fa2-5fd35b2c38a9 · outbound

This paper cites and Van Roy, B.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Van Roy, B

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:24.139825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:24.139825Z digest=sha256:3e38e8270008b907a6af61b8a55b094a223a7b0687318386b439a2e83882ba93

Observation 865994b7-6787-4ecf-b454-598dd2ac2922 · outbound

This paper cites V., Kazerouni, A., Osband, I., and Wen, Z.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret V., Kazerouni, A., Osband, I., and Wen, Z

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.369237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.145764Z digest=sha256:76f634a857465b526cbb20a4f1796f974788018eab05c75699d9cb4f2cb43caa

Observation 4c6b7d21-9e6d-4d1e-a823-980ab814181e · outbound

This paper cites Posterior sampling for deep reinforcement learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Posterior sampling for deep reinforcement learning

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.353788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.151068Z digest=sha256:376b836c43c4aa55e341cf93cadb3b6bb83b3a53f35e542f64c2c44ba0b92321

Observation 67a7d357-6d5d-48dc-9a23-1351b4cdcade · outbound

This paper cites Poincar \'e and log--sobolev inequalities for mixtures.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Poincar \'e and log--sobolev inequalities for mixtures

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.338354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.157014Z digest=sha256:5e48791112981e25d6a2fa8be3c4611d8d2fe14b27592041f9c140b9b2aee166

Observation dcedeef4-12cd-4f51-b44e-4f16f236a0f9 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Proximal Policy Optimization Algorithms

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:24.162657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:24.162657Z digest=sha256:fe7cc6c78b32528eeb5ed1043d83be98351bc4d0027e7d4f856c02497eb2ef53

Observation 91946533-3031-46d3-9a33-f84cd1bc70ba · outbound

This paper cites J., Lykouris, T., Dudik, M., and Schapire, R.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret J., Lykouris, T., Dudik, M., and Schapire, R

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.321985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.168521Z digest=sha256:c1661ee81750973fa689f4c1390ef3e5524c12ff6c3dc289ce277f86d23a32b3

Observation cb698d2f-3b88-4fe9-99fa-afd993b76714 · outbound

This paper cites A feynman-kac approach for logarithmic sobolev inequalities, 2021.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret A feynman-kac approach for logarithmic sobolev inequalities, 2021

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.307584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.173953Z digest=sha256:ba5ac2f36165b3b1113f8ad1735c53fe017a819134b286ec83c37c3bcccc39a3

Observation 55f8f941-d5c9-4251-9347-1ab064ce0a05 · outbound

This paper cites an unresolved cited work.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Unresolved cited work

Reference 84

Resolution
unresolved
raw_fallback, observed 2026-08-10T23:21:25.291574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.179095Z digest=sha256:6c4a87228cc19d582377c25f3a5c64df6435bf10374e3ccbb9c278a41066c784

Observation 69c7b25d-f804-4d46-b499-c1a11e5a12be · outbound

This paper cites On the Likelihood that One Unknown Probability Exceeds Another in View of the Evidence of two Samples.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret On the Likelihood that One Unknown Probability Exceeds Another in View of the Evidence of two Samples

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.276278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.184463Z digest=sha256:85c5cf0c4fc3ec9cfaa1e6d7fe7d38e12d3373f4297580c6fffc5dd89c697b21

Observation 76dbb519-25b1-4a83-bded-7e450c2bfbcc · outbound

This paper cites Mujoco: A physics engine for model-based control.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Mujoco: A physics engine for model-based control

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:24.189786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:24.189786Z digest=sha256:133b2de0750344a09fd2959df4a2f7984560ceb82216de06963f76b70c560bb0

Observation 3343825b-824d-43ed-9c0c-d8821252c97a · outbound

This paper cites Gymnasium: A Standard Interface for Reinforcement Learning Environments.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Gymnasium: A Standard Interface for Reinforcement Learning Environments

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:24.195351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:24.195351Z digest=sha256:1e007bc7dd724e872489a34ba43e310aa98d4d36d0210b6404e0ae202e8f74ec

Observation e8a53be0-225b-4b4f-8b39-24c0c5020054 · outbound

This paper cites and Wibisono, A.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Wibisono, A

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.261377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.200404Z digest=sha256:a380414dbbd3b23f44fbf88a5a66ceecffe95dc3b5eb9ccafee8061bef537adf

Observation 7008a02b-415f-42b3-8947-9d233ef03e9e · outbound

This paper cites an unresolved cited work.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Unresolved cited work

Reference 89

Resolution
unresolved
raw_fallback, observed 2026-08-10T23:21:25.245553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.206184Z digest=sha256:0bc99692b944d68dc02ff7723e254f9d9d3b93281ae6c820f8aa5870850cf199

Observation 03612133-d4c6-4eea-8e7a-6d0c86f428eb · outbound

This paper cites Logarithmic sobolev inequalities: conditions and counterexamples.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Logarithmic sobolev inequalities: conditions and counterexamples

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.229534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.211047Z digest=sha256:7f78fbcda4f5efbb8b83419c0ad3793655055530ebac9b6a6fea8efef2700147

Observation 6ca492d4-4043-4614-961f-09dae7458570 · outbound

This paper cites and Ghosal, S.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret and Ghosal, S

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.209893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.216386Z digest=sha256:3ee47e8819549d9d837238b2598c4fc74c0f31ce4de8550e7c98f17c1b9adbc5

Observation 4a70c2b1-2396-4ab6-a829-3c527d9eb2c8 · outbound

This paper cites V., Azizzadenesheli, K., and Anandkumar, A.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret V., Azizzadenesheli, K., and Anandkumar, A

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.191355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.221108Z digest=sha256:df3adefca47b5a5cafd9bb8970547f0884f8785b01e77e6b86d4c660742bdeb8

Observation 6e7353e7-4209-44fd-9280-8ea226b52d8e · outbound

This paper cites Mean field langevin actor-critic: Faster convergence and global optimality beyond lazy learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Mean field langevin actor-critic: Faster convergence and global optimality beyond lazy learning

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.174268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.225855Z digest=sha256:0654a847568e210605e8bbe9c63eb2c7303c15ccf6c02b6145baf1f5279249e4

Observation f10bf7b1-3495-47b8-95d3-cfff16234755 · outbound

This paper cites Accelerating approximate T hompson sampling with underdamped L angevin M onte C arlo.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Accelerating approximate T hompson sampling with underdamped L angevin M onte C arlo

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.157485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.230749Z digest=sha256:c0a2115ab3f8b4de714716d596ed1fa3d0482be2a660ff49447df3613d4ce25e

Observation f9931586-750f-4ca2-9d73-405d08c23b59 · outbound

This paper cites Varibad: variational bayes-adaptive deep rl via meta-learning.

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret Varibad: variational bayes-adaptive deep rl via meta-learning

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T23:21:25.139810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-10T23:21:24.235396Z digest=sha256:2b5d076d46f2d71a2554b26b529b0c211c02518c96d1abdb592135532d009fba

Pith citing papers

No inbound Pith citation observations are available.