Paper Citation Record · LEDGER

Position: Curvature Matrices Should Be Democratized via Linear Operators

As of 19 August 2026, this Paper Citation Record lists 100 of 103 outbound references and 4 inbound Pith citation observations for arXiv:2501.19183.

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

pith.paper-citation-record.v1
2501.19183 v1

Coverage vector

measured 100 of 103 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T21:05:49.174147Z

measured 104 of 104 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:03:56.569578Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

100 of 103 outbound references displayed

verified exact1
verified fuzzy48
unresolved51
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 42188947-0b92-4a57-81e7-3454730b3e53 · outbound

This paper cites write newline.

Position: Curvature Matrices Should Be Democratized via Linear Operators write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.824004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fc80a5c-5b29-4c0e-a9d6-f3f6bbcfa8f4 · outbound

This paper cites Natural gradient works efficiently in learning.

Position: Curvature Matrices Should Be Democratized via Linear Operators Natural gradient works efficiently in learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.829191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3188f01a-c2f2-49f1-adcc-484199b4ce07 · outbound

This paper cites An estimator for the diagonal of a matrix.

Position: Curvature Matrices Should Be Democratized via Linear Operators An estimator for the diagonal of a matrix

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.833368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a8aef5-4b57-4658-863a-4f60c470c412 · outbound

This paper cites Gradient descent on neurons and its link to approximate second-order optimization.

Position: Curvature Matrices Should Be Democratized via Linear Operators Gradient descent on neurons and its link to approximate second-order optimization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.837656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33f2f59c-6bdb-404f-8c8c-848adbf5ab45 · outbound

This paper cites Exact natural gradient in deep linear networks and its application to the nonlinear case.

Position: Curvature Matrices Should Be Democratized via Linear Operators Exact natural gradient in deep linear networks and its application to the nonlinear case

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.841320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06103c8f-37ae-4f6c-a5dd-a8cd6af4b383 · outbound

This paper cites and Bergholm, V.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Bergholm, V

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.845091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abb6e1a2-0a66-409e-9db9-361198619630 · outbound

This paper cites Practical G auss- N ewton optimisation for deep learning.

Position: Curvature Matrices Should Be Democratized via Linear Operators Practical G auss- N ewton optimisation for deep learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.848798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f805b4d-4cb2-49bd-ab27-b46df7416515 · outbound

This paper cites J., Leary, C., Maclaurin, D., and Wanderman-Milne, S.

Position: Curvature Matrices Should Be Democratized via Linear Operators J., Leary, C., Maclaurin, D., and Wanderman-Milne, S

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.852637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99c42b98-0a8c-4c35-b722-6521c3d94e1a · outbound

This paper cites and van Handel , R.

Position: Curvature Matrices Should Be Democratized via Linear Operators and van Handel , R

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.856183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aee819df-a7aa-4368-9f17-90e1616d45b1 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.859705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e2cd292-8222-4157-96cd-672c05e4010c · outbound

This paper cites A., Collin, F.-D., and Durif, G.

Position: Curvature Matrices Should Be Democratized via Linear Operators A., Collin, F.-D., and Durif, G

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.863037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57523fbe-94e9-4eed-af61-ce4b178ba29a · outbound

This paper cites Efficient second-order optimization for neural networks with kernel machines.

Position: Curvature Matrices Should Be Democratized via Linear Operators Efficient second-order optimization for neural networks with kernel machines

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.866444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf6635e-5185-4255-b792-7427a02d41f0 · outbound

This paper cites How to compute hessian-vector products? In International Conference on Learning Representations (ICLR) Blogposts, 2024.

Position: Curvature Matrices Should Be Democratized via Linear Operators How to compute hessian-vector products? In International Conference on Learning Representations (ICLR) Blogposts, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.869918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93344926-cb38-4d05-8439-787d7972008c · outbound

This paper cites B ack PACK : Packing more into backprop.

Position: Curvature Matrices Should Be Democratized via Linear Operators B ack PACK : Packing more into backprop

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.873379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bc9a56d-39a4-44b8-b02d-6f59e2374088 · outbound

This paper cites Vi V i T : Curvature access through the generalized gauss-newton s low-rank structure.

Position: Curvature Matrices Should Be Democratized via Linear Operators Vi V i T : Curvature access through the generalized gauss-newton s low-rank structure

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.876767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cc25e2e-e1a9-4466-a417-90601e819390 · outbound

This paper cites Learning fast algorithms for linear transforms using butterfly factorizations.

Position: Curvature Matrices Should Be Democratized via Linear Operators Learning fast algorithms for linear transforms using butterfly factorizations

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.879994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a6c051a-43a4-454e-9e92-2a461cbd0751 · outbound

This paper cites S., Desai, A., Poli, M., Grogan, J., Liu, A., Rao, A., Rudra, A., and R \'e , C.

Position: Curvature Matrices Should Be Democratized via Linear Operators S., Desai, A., Poli, M., Grogan, J., Liu, A., Rao, A., Rudra, A., and R \'e , C

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.883330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 590f4071-4729-43d2-9143-e37eed7b3ba6 · outbound

This paper cites Laplace redux - effortless bayesian deep learning.

Position: Curvature Matrices Should Be Democratized via Linear Operators Laplace redux - effortless bayesian deep learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.886691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a1aaf1-8fe0-4547-9ebd-c4847708ae62 · outbound

This paper cites and Mahoney, M.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Mahoney, M

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.889884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4535eb-08f3-4a16-83cd-47b7db5ad040 · outbound

This paper cites N., Tropp, J.

Position: Curvature Matrices Should Be Democratized via Linear Operators N., Tropp, J

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.893382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28a4b32b-0c4e-4d8d-b4e7-08db9adf1a96 · outbound

This paper cites E., Schneider, F., and Hennig, P.

Position: Curvature Matrices Should Be Democratized via Linear Operators E., Schneider, F., and Hennig, P

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.896769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd187990-edf3-4d4f-b82d-d8cbafa44841 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.900157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8f26073-fc47-4654-8496-fa7b028b6e42 · outbound

This paper cites S kerch: Sketched matrix decompositions for PyTorch , 2024.

Position: Curvature Matrices Should Be Democratized via Linear Operators S kerch: Sketched matrix decompositions for PyTorch , 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.903196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68576484-c27d-4a6e-9ebc-fd58a1843cda · outbound

This paper cites and Hodges, J.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Hodges, J

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.088586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f58a0cfd-0571-4473-8209-7b1befbf6ff2 · outbound

This paper cites and Saunders, M.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Saunders, M

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.078160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a9540c5e-8b92-4fe0-8fa6-4d899f95751c · outbound

This paper cites M-fac: Efficient matrix-free approximations of second-order information.

Position: Curvature Matrices Should Be Democratized via Linear Operators M-fac: Efficient matrix-free approximations of second-order information

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.067815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c311cbf8-a7b4-4615-81c1-0cdaf3f14d3b · outbound

This paper cites Q., Bindel, D., and Wilson, A.

Position: Curvature Matrices Should Be Democratized via Linear Operators Q., Bindel, D., and Wilson, A

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.057231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4f056ef8-e516-45ec-8857-54d79dfdb5e9 · outbound

This paper cites Fast approximate natural gradient descent in a kronecker-factored eigenbasis, 2018.

Position: Curvature Matrices Should Be Democratized via Linear Operators Fast approximate natural gradient descent in a kronecker-factored eigenbasis, 2018

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.045336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f44c55e9-7715-4334-9670-710a42187e17 · outbound

This paper cites Eigenvalue and generalized eigenvalue problems: Tutorial, 2019.

Position: Curvature Matrices Should Be Democratized via Linear Operators Eigenvalue and generalized eigenvalue problems: Tutorial, 2019

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.033898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d0717276-f24c-476a-a572-e6d137cebb88 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:50.023024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7c860ac1-3029-4930-81f8-a5a7bd44ae3b · outbound

This paper cites pytorch-hessian-eigenthings: efficient pytorch hessian eigendecomposition, 2018.

Position: Curvature Matrices Should Be Democratized via Linear Operators pytorch-hessian-eigenthings: efficient pytorch hessian eigendecomposition, 2018

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.012233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 58f88bd5-2197-442c-9c89-dbc81d752e28 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.934847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90d1f98f-3728-48cc-a706-12dc5cc19baa · outbound

This paper cites Deep curvature suite, 2019.

Position: Curvature Matrices Should Be Democratized via Linear Operators Deep curvature suite, 2019

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:50.001268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c01cf163-9475-44d5-b958-42747fa30796 · outbound

This paper cites and Martens, J.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Martens, J

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.941560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b819723c-f945-436c-992e-1d374028906d · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.945137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbbe5b2a-acca-4d6c-a021-9f5689a587b1 · outbound

This paper cites A., and Dyer, E.

Position: Curvature Matrices Should Be Democratized via Linear Operators A., and Dyer, E

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.978791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fe84bade-3017-42f1-b2d5-8f2734f1004f · outbound

This paper cites G., and Tropp, J.

Position: Curvature Matrices Should Be Democratized via Linear Operators G., and Tropp, J

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.968704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eb4518fc-891f-4f51-9d8d-d11e63afd349 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.958554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dbfefa46-b00f-47d1-90db-8c5ad03872f0 · outbound

This paper cites Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks.

Position: Curvature Matrices Should Be Democratized via Linear Operators Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-09T21:05:49.259302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 145248e4-5ef0-4eff-9105-bb818855ce61 · outbound

This paper cites R., Millman, K.

Position: Curvature Matrices Should Be Democratized via Linear Operators R., Millman, K

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.947818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8c370f87-5b3b-4ef5-a7f9-ef0a7a02fc15 · outbound

This paper cites and Stork, D.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Stork, D

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.936684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4b41cf04-289a-41d2-9cfe-f45ab44a7915 · outbound

This paper cites Deep residual learning for image recognition.

Position: Curvature Matrices Should Be Democratized via Linear Operators Deep residual learning for image recognition

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.925814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9771f774-3259-4c09-a8bc-080f446815ce · outbound

This paper cites On ``natural'' learning and pruning in multilayered perceptrons.

Position: Curvature Matrices Should Be Democratized via Linear Operators On ``natural'' learning and pruning in multilayered perceptrons

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.915083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cf0c100f-4fbc-4ab9-a6f3-86919466bd58 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.904879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6fb8c461-9251-47e7-8f95-72e7da52a45d · outbound

This paper cites A stochastic estimator of the trace of the influence matrix for laplacian smoothing splines.

Position: Curvature Matrices Should Be Democratized via Linear Operators A stochastic estimator of the trace of the influence matrix for laplacian smoothing splines

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.894956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 56e5ab77-0924-4762-bdc1-d8450cbd4505 · outbound

This paper cites and Szegedy, C.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Szegedy, C

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:48.984216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29292cc1-c281-40c6-8946-9b7437f7453f · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

Position: Curvature Matrices Should Be Democratized via Linear Operators Neural tangent kernel: Convergence and generalization in neural networks

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.878459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0be3fddd-d6c1-470a-bc80-47854cb9a084 · outbound

This paper cites The simplest, fastest repository for training/finetuning medium-sized gpts., 2022.

Position: Curvature Matrices Should Be Democratized via Linear Operators The simplest, fastest repository for training/finetuning medium-sized gpts., 2022

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.868131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fb0f7c8d-a087-4973-8d0f-f6b0c934d613 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.858002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 77a9738d-d90b-4cb4-95ab-81a0098eabc8 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.847887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c73bedf8-a698-4455-94b5-8e736c1128f1 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.837130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8246afb8-bdb0-4cac-add7-1be849f2c8dd · outbound

This paper cites A sober look at LLMs for material discovery: Are they actually good for B ayesian optimization over molecules? In International Conference on Machine Learning (ICML), 2024.

Position: Curvature Matrices Should Be Democratized via Linear Operators A sober look at LLMs for material discovery: Are they actually good for B ayesian optimization over molecules? In International Conference on Machine Learning (ICML), 2024

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.827171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d4bacef8-0960-4cb7-8053-f1c24c4032d9 · outbound

This paper cites Limitations of the empirical fisher approximation for natural gradient descent.

Position: Curvature Matrices Should Be Democratized via Linear Operators Limitations of the empirical fisher approximation for natural gradient descent

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.814856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 488af8d6-5213-4843-84ad-bc83b7ed959a · outbound

This paper cites Optimal brain damage.

Position: Curvature Matrices Should Be Democratized via Linear Operators Optimal brain damage

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.802761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 04564129-8b54-4bfe-961d-feca3b64a580 · outbound

This paper cites B., Sorensen, D.

Position: Curvature Matrices Should Be Democratized via Linear Operators B., Sorensen, D

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.791408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0321cdd7-ccea-46f1-9205-ff2ba34996fa · outbound

This paper cites E., and Grosse, R.

Position: Curvature Matrices Should Be Democratized via Linear Operators E., and Grosse, R

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.779542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 75ce3f7d-f167-408b-8aa7-a6a50e9e7483 · outbound

This paper cites E., and Makhzani, A.

Position: Curvature Matrices Should Be Democratized via Linear Operators E., and Makhzani, A

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.767642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1bac6cfd-dcd2-496c-816b-3cae0746e6ee · outbound

This paper cites E., and Makhzani, A.

Position: Curvature Matrices Should Be Democratized via Linear Operators E., and Makhzani, A

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.755661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b5b848a-7a9c-4a61-9698-ac6dd3b9103c · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.742916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 95fb7847-466f-42d3-b1d9-b0dc7a25ea5f · outbound

This paper cites Optimizing millions of hyperparameters by implicit differentiation.

Position: Curvature Matrices Should Be Democratized via Linear Operators Optimizing millions of hyperparameters by implicit differentiation

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.730045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e63224d-c483-4e39-919d-bc445b8ca523 · outbound

This paper cites Indiscriminate data poisoning attacks on neural networks.

Position: Curvature Matrices Should Be Democratized via Linear Operators Indiscriminate data poisoning attacks on neural networks

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.718005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 180bd444-ec5f-4b28-a8a9-d3da2c17cdd9 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.705879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 53bf8b4c-892d-4e6f-b9c6-63e3aebfd1ff · outbound

This paper cites Deep learning via H essian-free optimization.

Position: Curvature Matrices Should Be Democratized via Linear Operators Deep learning via H essian-free optimization

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.694668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b284592-8bdf-475d-82f8-88dd59b6682c · outbound

This paper cites New insights and perspectives on the natural gradient method, 2020.

Position: Curvature Matrices Should Be Democratized via Linear Operators New insights and perspectives on the natural gradient method, 2020

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.682915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0e100d61-9143-4165-8b01-0adc6a75b85b · outbound

This paper cites and Grosse, R.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Grosse, R

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.050216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1895726-cf78-4b15-968d-604718faaeb3 · outbound

This paper cites and Sutskever, I.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Sutskever, I

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.663047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2c741fdc-6423-47d5-9578-9243475b146f · outbound

This paper cites Kronecker-factored curvature approximations for recurrent neural networks.

Position: Curvature Matrices Should Be Democratized via Linear Operators Kronecker-factored curvature approximations for recurrent neural networks

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.650925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 25625161-3dad-403b-a502-5134e5d1beb3 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.638327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7703bee8-d909-41fe-9a3f-7ac9ec680d88 · outbound

This paper cites A., Musco, C., Musco, C., and Woodruff, D.

Position: Curvature Matrices Should Be Democratized via Linear Operators A., Musco, C., Musco, C., and Woodruff, D

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.626691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 79961669-60ce-42a3-98df-0870579fef0a · outbound

This paper cites Influence functions for scalable data attribution in diffusion models.

Position: Curvature Matrices Should Be Democratized via Linear Operators Influence functions for scalable data attribution in diffusion models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.068690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b18a451-1c43-4338-8d6e-02842ea515a7 · outbound

This paper cites Asdl: A unified interface for gradient preconditioning in pytorch, 2023.

Position: Curvature Matrices Should Be Democratized via Linear Operators Asdl: A unified interface for gradient preconditioning in pytorch, 2023

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.072180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c32c376-3f7f-47eb-9466-7f8ae6051b71 · outbound

This paper cites Measurements of three-level hierarchical structure in the outliers in the spectrum of deepnet H essians.

Position: Curvature Matrices Should Be Democratized via Linear Operators Measurements of three-level hierarchical structure in the outliers in the spectrum of deepnet H essians

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.597419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 122c239c-e53f-48f6-b9e6-343d9096390b · outbound

This paper cites The full spectrum of deepnet hessians at scale: Dynamics with sgd training and sample size, 2019 b.

Position: Curvature Matrices Should Be Democratized via Linear Operators The full spectrum of deepnet hessians at scale: Dynamics with sgd training and sample size, 2019 b

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.585394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b80c52c4-6d23-4b64-aefa-551a693d6145 · outbound

This paper cites Y., and Donoho, D.

Position: Curvature Matrices Should Be Democratized via Linear Operators Y., and Donoho, D

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.573411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14ddf7e5-f2b6-4f1d-98d9-7b940e094cce · outbound

This paper cites PyTorch : An imperative style, high-performance deep learning library.

Position: Curvature Matrices Should Be Democratized via Linear Operators PyTorch : An imperative style, high-performance deep learning library

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.561109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 31a40507-dd62-4486-93ae-67467534042a · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.089340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa66f4ab-19f3-41ca-a04d-1ac4c3658a29 · outbound

This paper cites Applications of negative dimensional tensors.

Position: Curvature Matrices Should Be Democratized via Linear Operators Applications of negative dimensional tensors

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.540933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8515148f-b8bd-4166-8c63-fa55158131c6 · outbound

This paper cites ISAAC newton: Input-based approximate curvature for newton's method.

Position: Curvature Matrices Should Be Democratized via Linear Operators ISAAC newton: Input-based approximate curvature for newton's method

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.096450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3db9f3-b345-48af-ae56-221f11f76139 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.519937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8e653d5e-3553-4805-81ab-cddadba79bc3 · outbound

This paper cites A., Ferri, C., Chen, Z., Goldblum, M., Bruss, C.

Position: Curvature Matrices Should Be Democratized via Linear Operators A., Ferri, C., Chen, Z., Goldblum, M., Bruss, C

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.507091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e1e66cb9-c189-4fc2-8806-8a89f0fef809 · outbound

This paper cites Lineax: unified linear solves and linear least-squares in jax and equinox.

Position: Curvature Matrices Should Be Democratized via Linear Operators Lineax: unified linear solves and linear least-squares in jax and equinox

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.493754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 189092fe-1ce0-46d3-9e5f-092023ed9722 · outbound

This paper cites PyLops -- A Linear-Operator Python Library for large scale optimization.

Position: Curvature Matrices Should Be Democratized via Linear Operators PyLops -- A Linear-Operator Python Library for large scale optimization

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.109728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44df82b7-53f1-4e80-962b-7e9fbd1ec8eb · outbound

This paper cites and Goldfarb, D.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Goldfarb, D

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.481722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1c0a7f12-e174-427c-b800-86c730d29b35 · outbound

This paper cites Eigenvalues of the hessian in deep learning: Singularity and beyond, 2017.

Position: Curvature Matrices Should Be Democratized via Linear Operators Eigenvalues of the hessian in deep learning: Singularity and beyond, 2017

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.469040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 876f7db8-2373-422b-96f9-56284a041c75 · outbound

This paper cites U., Dauphin, Y., and Bottou, L.

Position: Curvature Matrices Should Be Democratized via Linear Operators U., Dauphin, Y., and Bottou, L

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.456584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9dad4322-2aed-4e01-9bc5-50607a698707 · outbound

This paper cites Cockpit: A practical debugging tool for the training of deep neural networks.

Position: Curvature Matrices Should Be Democratized via Linear Operators Cockpit: A practical debugging tool for the training of deep neural networks

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.444391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7722be34-29ce-45dd-86c4-0f0dc7d94b36 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.127255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a3d7fc-c634-4de3-991f-946a7217c4ec · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 88

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.423859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ae6bd903-e30d-410c-8d8e-1ba09db1ede3 · outbound

This paper cites P., Bachmann, G., and Hofmann, T.

Position: Curvature Matrices Should Be Democratized via Linear Operators P., Bachmann, G., and Hofmann, T

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.412157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ceef937-a174-436b-a6c1-6ed0d950ab5c · outbound

This paper cites How to guess a gradient.

Position: Curvature Matrices Should Be Democratized via Linear Operators How to guess a gradient

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.137940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61394b48-dae7-4839-9c41-f3cb29f6b979 · outbound

This paper cites and Sun, K.

Position: Curvature Matrices Should Be Democratized via Linear Operators and Sun, K

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.400175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b0f1e700-3e73-42a7-adda-e012b2532adc · outbound

This paper cites Dropout: A simple way to prevent neural networks from overfitting.

Position: Curvature Matrices Should Be Democratized via Linear Operators Dropout: A simple way to prevent neural networks from overfitting

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.387126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 37edbca1-e069-4ad0-8232-b50f1d9fd7df · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 93

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.374758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8d06bb6e-5c95-4de0-823d-b99970a53b77 · outbound

This paper cites Debiasing mini-batch quadratics for applications in deep learning, 2024.

Position: Curvature Matrices Should Be Democratized via Linear Operators Debiasing mini-batch quadratics for applications in deep learning, 2024

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.362560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df713798-eee3-4509-8a30-39c756b242ae · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.156309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c9f2e6-ed25-45cb-87dc-9ad9eb86b898 · outbound

This paper cites A., Yurtsever, A., Udell, M., and Cevher, V.

Position: Curvature Matrices Should Be Democratized via Linear Operators A., Yurtsever, A., Udell, M., and Cevher, V

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.350256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ad10dbb2-9fb2-4734-9fc3-f7af5af6449d · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 97

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.337793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cb7ac99c-b8f9-42a6-92cf-44d813d5dba5 · outbound

This paper cites N., Kaiser, L.

Position: Curvature Matrices Should Be Democratized via Linear Operators N., Kaiser, L

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-09T21:05:49.167090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e808fb6d-07dd-4210-97aa-749f4415a16d · outbound

This paper cites E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., van der Walt , S.

Position: Curvature Matrices Should Be Democratized via Linear Operators E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., van der Walt , S

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T21:05:49.316830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2c9a4481-1568-4e4e-b313-6c0f20024954 · outbound

This paper cites an unresolved cited work.

Position: Curvature Matrices Should Be Democratized via Linear Operators Unresolved cited work

Reference 100

Resolution: unresolved; raw_fallback, observed 2026-08-09T21:05:49.305406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 1d293932-d2ee-44c1-a119-01f3db328bc0 · inbound

laplax -- Laplace Approximations with JAX cites this paper.

laplax -- Laplace Approximations with JAX Position: Curvature Matrices Should Be Democratized via Linear Operators

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T15:03:56.569578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d1c2735-3f55-4f34-9ad5-fa83b1959693 · inbound

Bayesian Fine-tuning in Projected Subspaces cites this paper.

Bayesian Fine-tuning in Projected Subspaces Position: Curvature Matrices Should Be Democratized via Linear Operators

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:56.267884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 521d9cbf-5923-4d5a-823a-f8fcd4998f7e · inbound

Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss cites this paper.

Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss Position: Curvature Matrices Should Be Democratized via Linear Operators

Reference 82

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T11:56:56.085888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cf95413f-549a-47fa-b59c-bbea90b59cf6 · inbound

Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior cites this paper.

Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior Position: Curvature Matrices Should Be Democratized via Linear Operators

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-06-26T08:49:14.982272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.