Paper Citation Record · LEDGER

The Convergence Behavior of Adam under Heavy-Tailed Noise

As of 18 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2607.27383.

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

pith.paper-citation-record.v1
2607.27383 v2

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T03:30:54.259100Z

measured 16 of 16 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 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

16 of 16 outbound references displayed

verified exact0
verified fuzzy0
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 057fc1c3-65aa-48c1-b948-718d23632291 · outbound

This paper cites Adam with model exponential moving average is effective for nonconvex optimization.

The Convergence Behavior of Adam under Heavy-Tailed Noise Adam with model exponential moving average is effective for nonconvex optimization

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.186249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f5ce516-822f-48ed-abe7-699a88d21185 · outbound

This paper cites Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed.

The Convergence Behavior of Adam under Heavy-Tailed Noise Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.201487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2077a73f-f5ac-4a88-af18-2cb11ca908cb · outbound

This paper cites Tight lower bounds and optimal algo- rithms for stochastic nonconvex optimization with heavy- tailed noise.arXiv preprint arXiv:2512.18713,.

The Convergence Behavior of Adam under Heavy-Tailed Noise Tight lower bounds and optimal algo- rithms for stochastic nonconvex optimization with heavy- tailed noise.arXiv preprint arXiv:2512.18713,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.206059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa4c358-96de-4de1-bab1-03b873491558 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

The Convergence Behavior of Adam under Heavy-Tailed Noise Adam: A Method for Stochastic Optimization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.215541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc3bb81-7dd4-4301-b9cb-1ed16a0eff20 · outbound

This paper cites Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tails.

The Convergence Behavior of Adam under Heavy-Tailed Noise Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tails

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.224484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44966eed-a081-43ab-a8dd-abfce0d8fe99 · outbound

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

The Convergence Behavior of Adam under Heavy-Tailed Noise Online Learning: A Modern Introduction Using Convex Optimization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.229017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfc4c456-b8f6-4af4-bda5-f58474b9621c · outbound

This paper cites nX t=1 βn−tξt # ≤D E.

The Convergence Behavior of Adam under Heavy-Tailed Noise nX t=1 βn−tξt # ≤D E

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.253753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95ac23b0-01e3-4a7e-9433-4e62d1fb49e0 · outbound

This paper cites TX n=1 nX t=1 (1−β)β n−t F(x t)−F(x t−1) | {z } A # +E.

The Convergence Behavior of Adam under Heavy-Tailed Noise TX n=1 nX t=1 (1−β)β n−t F(x t)−F(x t−1) | {z } A # +E

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.259100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc59623a-1595-41db-8481-7ea3b8129fe2 · outbound

This paper cites Gradient normaliza- tion provably benefits nonconvex sgd under heavy-tailed noise.arXiv preprint arXiv:2410.16561, page 5,.

The Convergence Behavior of Adam under Heavy-Tailed Noise Gradient normaliza- tion provably benefits nonconvex sgd under heavy-tailed noise.arXiv preprint arXiv:2410.16561, page 5,

Reference 1951

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.233552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4272acfc-0d61-495e-b5f9-2535fc879119 · outbound

This paper cites Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise.

The Convergence Behavior of Adam under Heavy-Tailed Noise Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise

Reference 1965

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.238431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecc26b0c-424d-49a5-9fd4-394d553971f5 · outbound

This paper cites Online convex optimization with heavy tails: Old algorithms, new regrets, and applications.arXiv preprint arXiv:2508.07473,.

The Convergence Behavior of Adam under Heavy-Tailed Noise Online convex optimization with heavy tails: Old algorithms, new regrets, and applications.arXiv preprint arXiv:2508.07473,

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.220399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebb08232-41ec-4f63-b1f3-decb387c9692 · outbound

This paper cites Complexity of normalized stochastic first-order methods with momentum under heavy-tailed noise.arXiv preprint arXiv:2506.11214,.

The Convergence Behavior of Adam under Heavy-Tailed Noise Complexity of normalized stochastic first-order methods with momentum under heavy-tailed noise.arXiv preprint arXiv:2506.11214,

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.210427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0e9cb4b-09f8-4bce-b656-cf8b2f057ef0 · outbound

This paper cites Random scaling and mo- mentum for non-smooth non-convex optimization.arXiv preprint arXiv:2405.09742,.

The Convergence Behavior of Adam under Heavy-Tailed Noise Random scaling and mo- mentum for non-smooth non-convex optimization.arXiv preprint arXiv:2405.09742,

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.248635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8009794d-f415-4b92-a176-1dd385029e5e · outbound

This paper cites General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization.

The Convergence Behavior of Adam under Heavy-Tailed Noise General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.196645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05b88bd0-d395-4f1b-8db1-dd7b93dd0aa7 · outbound

This paper cites Linear attention is (maybe) all you need (to understand transformer optimization).

The Convergence Behavior of Adam under Heavy-Tailed Noise Linear attention is (maybe) all you need (to understand transformer optimization)

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.192015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94d398b3-5b16-44b0-ada8-31b52e053153 · outbound

This paper cites Why gradient clipping accelerates training: A theoretical justification for adaptivity.

The Convergence Behavior of Adam under Heavy-Tailed Noise Why gradient clipping accelerates training: A theoretical justification for adaptivity

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-04T03:30:54.243075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.