Pith. sign in

Paper Citation Record · LEDGER

Efficient Distributed Optimization under Heavy-Tailed Noise

As of 10 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 4 inbound Pith citation observations for arXiv:2502.04164.

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

pith.paper-citation-record.v1
2502.04164 v2

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T23:25:10.683435Z

measured 19 of 19 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T16:23:19.534857Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T21:56:15.628231Z

Reference resolution

15 of 15 outbound references displayed

  • verified exact1
  • verified fuzzy9
  • unresolved5
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3224570d-ca0c-41ca-b271-05c3fabbba22 · outbound

This paper cites A Field Guide to Federated Optimization.

Efficient Distributed Optimization under Heavy-Tailed Noise A Field Guide to Federated Optimization

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-08T23:25:10.647358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T23:25:10.647358Z digest=sha256:9c5d01ac5a266bb388eea5eb81fe2c9eaa12e77dbf1196339c28eb0910d626ba

Observation 4874ca7c-6149-475c-af08-ecfccd1c3232 · outbound

This paper cites Rethinking Memory and Communication Cost for Efficient Large Language Model Training.

Efficient Distributed Optimization under Heavy-Tailed Noise Rethinking Memory and Communication Cost for Efficient Large Language Model Training

Reference 6

Resolution
verified exact
local_arxiv, observed 2026-08-08T23:25:10.730519Z

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=pdf_text observed=2026-08-08T23:25:10.650999Z digest=sha256:9ccef19d0215dc7fd1e8d3a5fe67c0172faec3ed4a17a76c72c640a9d85213b0

Observation b74541a3-d9ef-456f-87cf-c1c5d6c37342 · outbound

This paper cites Qwen3 Technical Report.

Efficient Distributed Optimization under Heavy-Tailed Noise Qwen3 Technical Report

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-08T23:25:10.654885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T23:25:10.654885Z digest=sha256:f988f056101cec0487146830b4c1dd566dbad61712070e20603178eb3d12d166

Observation 59b0bb1d-61a2-4e04-94c5-25f3d7be6b8c · outbound

This paper cites Such results elucidate the additional difficulties induced by efforts to remove the bounded gradient condition.

Efficient Distributed Optimization under Heavy-Tailed Noise Such results elucidate the additional difficulties induced by efforts to remove the bounded gradient condition

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.806924Z

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=pdf_text observed=2026-08-08T23:25:10.669207Z digest=sha256:57778af2d2f0fe0fbec72fa4e6232d94b6ae9f7a2504432d0dbcf91e72fe6f9e

Observation 24bfd7e7-6728-4022-8bb1-728f4fcff3bf · outbound

This paper cites Can the algorithm decrease distance to the true w∗ or not?.

Efficient Distributed Optimization under Heavy-Tailed Noise Can the algorithm decrease distance to the true w∗ or not?

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.789014Z

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=pdf_text observed=2026-08-08T23:25:10.676617Z digest=sha256:87e39ae4a6789a265ff669a94f364a279dc3a6a7df70ab840b00dc3f30d18635

Observation 5d272659-e35a-4798-b2e5-0ca37c106cf9 · outbound

This paper cites By incorporating datasets that span various linguistic challenges, GLUE provides a rigorous testbed for assessing the generalization capabilities of NLP models.

Efficient Distributed Optimization under Heavy-Tailed Noise By incorporating datasets that span various linguistic challenges, GLUE provides a rigorous testbed for assessing the generalization capabilities of NLP models

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.779615Z

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=pdf_text observed=2026-08-08T23:25:10.680098Z digest=sha256:19acafc51fa397890e0a3bdf98264f480de1c511c16c27996d7464883527aa3d

Observation edfb27bc-b8cb-49bd-bf48-481542a35e3f · outbound

This paper cites Generative Models We additionally evaluate our method using T5 (Raffel et al., 2020), a state-of-the-art text-to-text transformer model developed by Google Research.

Efficient Distributed Optimization under Heavy-Tailed Noise Generative Models We additionally evaluate our method using T5 (Raffel et al., 2020), a state-of-the-art text-to-text transformer model developed by Google Research

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.770046Z

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=pdf_text observed=2026-08-08T23:25:10.683435Z digest=sha256:b47e8cd7222ae00cf81a53b655b79a0d034dc3353b5a34a1e9b3d3a27e68f2f1

Observation 33446e0d-3a93-423a-9084-dbfb50686d64 · outbound

This paper cites and Chen, B.

Efficient Distributed Optimization under Heavy-Tailed Noise and Chen, B

Reference 2010

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.843814Z

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=pdf_text observed=2026-08-08T23:25:10.643664Z digest=sha256:211b7f8ddba941f9e1b42f301d5ccbd6b78ec1a79eaef269b52c8856dc483ed9

Observation 5b7643e7-acca-4ffd-b11e-1b2b9100777c · outbound

This paper cites an unresolved cited work.

Efficient Distributed Optimization under Heavy-Tailed Noise Unresolved cited work

Reference 2012

Resolution
unresolved
raw_fallback, observed 2026-08-08T23:25:10.825364Z

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=pdf_text observed=2026-08-08T23:25:10.662157Z digest=sha256:7afe76536044fc4e7f913a455acdd9f8ec9c022870951bb34cf0e1e87f92d546

Observation 149ca8d5-2ea9-48ed-80d9-fe15be0cfbf8 · outbound

This paper cites Overview of the iwslt 2017 evaluation campaign.

Efficient Distributed Optimization under Heavy-Tailed Noise Overview of the iwslt 2017 evaluation campaign

Reference 2018

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.852818Z

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=pdf_text observed=2026-08-08T23:25:10.632349Z digest=sha256:ff81960c60abd76ee74b645dde69fba36c0dd8b4daa842a27ad041e8f8379207

Observation 63e6757f-4e0e-4332-9742-3a10ca53c29c · outbound

This paper cites By finetuning RoBERTa on GLUE, we assess its generalization capabilities and robustness.

Efficient Distributed Optimization under Heavy-Tailed Noise By finetuning RoBERTa on GLUE, we assess its generalization capabilities and robustness

Reference 2019

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.798065Z

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=pdf_text observed=2026-08-08T23:25:10.673215Z digest=sha256:46ef7899cc4879c6037f4fc75cab881879757c53ffec2fad17c79692012b837a

Observation a4188f0c-1a37-4bed-9711-b058904b163d · outbound

This paper cites SQuAD: 100,000+ Questions for Machine Comprehension of Text.

Efficient Distributed Optimization under Heavy-Tailed Noise SQuAD: 100,000+ Questions for Machine Comprehension of Text

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-08T23:25:10.636231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T23:25:10.636231Z digest=sha256:e907b57893e487cdd6a708de45a20a0b23b9cc3e6cdcb8a632d63520b14dda96

Observation d272633e-84c3-4551-9f32-b3ad7aaeb6fd · outbound

This paper cites Local SGD Converges Fast and Communicates Little.

Efficient Distributed Optimization under Heavy-Tailed Noise Local SGD Converges Fast and Communicates Little

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-08T23:25:10.639899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T23:25:10.639899Z digest=sha256:03ac77291469e9031a1708f7c38b83b13bc5878ebbbff9a15c2316de1a663357

Observation c7fdc244-cff0-41df-9a20-ba775f23779a · outbound

This paper cites Their analysis reveals an inverse logarithmic dependence on the confidence level.

Efficient Distributed Optimization under Heavy-Tailed Noise Their analysis reveals an inverse logarithmic dependence on the confidence level

Reference 2023

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.816389Z

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=pdf_text observed=2026-08-08T23:25:10.665781Z digest=sha256:6667d504960c813e87001bffad0374f7a387694f326bdc463fe0d1318371a7c7

Observation d2cd17d3-1787-4b55-b2c4-392104097000 · outbound

This paper cites 15 C.2 Dynamics of Avg- L2Clip under Failing Compute Nodes.

Efficient Distributed Optimization under Heavy-Tailed Noise 15 C.2 Dynamics of Avg- L2Clip under Failing Compute Nodes

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T23:25:10.834534Z

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=pdf_text observed=2026-08-08T23:25:10.658625Z digest=sha256:206882f7289ff07a1eb54c9f84cbc303409ce6b45282c3ce065ce8c9fa82bd4b

Pith citing papers

Observation 83021658-c0d8-4c80-bc1a-9682767e7ce8 · inbound

Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence cites this paper.

Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence Efficient Distributed Optimization under Heavy-Tailed Noise

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-22T15:51:45.783447Z

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=pdf_text observed=2026-05-22T15:49:07.709952Z digest=sha256:e627265073f70ce186ff065095690004b71a385d3cd23e9abd73123fc69a138e

Observation 46c058ec-0070-4cb4-89be-994f0eb02d27 · inbound

Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise cites this paper.

Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise Efficient Distributed Optimization under Heavy-Tailed Noise

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-04T16:23:19.534857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T16:23:19.534857Z digest=sha256:ec1cb7afc88e7ea7fa3e8db2bba4f0cfa96cecd666121a51cb368d49dba29820

Observation bde2b1b6-02a2-44bd-86a1-2d5104aa394f · inbound

DeMuon: A Decentralized Muon for Matrix Optimization over Graphs cites this paper.

DeMuon: A Decentralized Muon for Matrix Optimization over Graphs Efficient Distributed Optimization under Heavy-Tailed Noise

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-04T13:25:35.212715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:25:35.212715Z digest=sha256:1e2539fc41c2831c9d13bd34a156c2fe042e214e7476dec930b69d8b34f601dd

Observation 62d921b8-eea2-4103-ab29-8a0c94fa8180 · inbound

A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling cites this paper.

A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling Efficient Distributed Optimization under Heavy-Tailed Noise

Reference 37

Resolution
verified exact
arxiv_id, observed 2026-07-01T21:56:15.629908Z

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=pdf_text observed=2026-06-28T16:03:26.866407Z digest=sha256:cf1a5649450baca10bab337cec64658dac7f3be4bb6a8ea0e60bd247cf380965