Paper Citation Record · LEDGER

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback

As of 21 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 0 inbound Pith citation observations for arXiv:2605.26373.

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

pith.paper-citation-record.v1
2605.26373 v1

Coverage vector

measured 6 of 6 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T22:13:07.433204Z

measured 6 of 6 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

6 of 6 outbound references displayed

verified exact4
verified fuzzy0
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 16b328e0-cd19-49c5-b2dc-6796b6040194 · outbound

This paper cites Stochastic optimization under hidden convexity.SIAM Journal on Optimization, 35(4):2544–2571, 2025a.

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback Stochastic optimization under hidden convexity.SIAM Journal on Optimization, 35(4):2544–2571, 2025a

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-29T22:13:59.322038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 59c7ef90-9276-4ba0-bad1-85df209dbfc0 · outbound

This paper cites Bandit convex optimisation.

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback Bandit convex optimisation

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-29T22:13:59.331521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 68a5c221-30eb-4e20-9a5a-2a82e56a9f18 · outbound

This paper cites Online Learning: A Modern Introduction Using Convex Optimization.

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback Online Learning: A Modern Introduction Using Convex Optimization

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:13:59.324494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eb1112e4-1d90-4fde-b0a1-6429bb2c7d43 · outbound

This paper cites Unveiling hidden convexity in deep learning: A sparse signal processing perspective.arXiv preprint arXiv:2603.23831,.

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback Unveiling hidden convexity in deep learning: A sparse signal processing perspective.arXiv preprint arXiv:2603.23831,

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T22:13:59.328124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b2540298-29d0-4d12-aeb8-803061fa7416 · outbound

This paper cites Using Assumption 2, we obtain: ∥Jεq t (q(xt+1))∥=∥J q−1(q(xt+1))−J q−1(yt)∥ ≤G∥q(x t+1)−y t∥ ≤ηG 2 ˆGF , where the last step uses the first estimate (i) proved above.

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback Using Assumption 2, we obtain: ∥Jεq t (q(xt+1))∥=∥J q−1(q(xt+1))−J q−1(yt)∥ ≤G∥q(x t+1)−y t∥ ≤ηG 2 ˆGF , where the last step uses the first estimate (i) proved above

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T22:13:07.433204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e80c4a7-e868-47ae-9f65-3f67a0428af0 · outbound

This paper cites We now control the norm of the bias∥bt∥ for any t.

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback We now control the norm of the bias∥bt∥ for any t

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T22:13:07.433204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.