Paper Citation Record · LEDGER

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2402.03220.

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

pith.paper-citation-record.v1
2402.03220 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 6 of 6 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:35:23.506017Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T17:37:13.926051Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation c6528430-18f8-46cb-a05c-c2d52ca77cd2 · inbound

There Will Be a Scientific Theory of Deep Learning cites this paper.

There Will Be a Scientific Theory of Deep Learning The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:21:09.292502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 12c77c28-e901-4be4-ab1c-8fc7d139f9a7 · inbound

The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently cites this paper.

The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Reference 126

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:31:24.313452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6dded3bc-1a6e-4a16-a286-4d1a550d8787 · inbound

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model cites this paper.

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Reference 168

Resolution: verified exact; arxiv_id, observed 2026-05-15T01:39:38.364520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 40d09592-5a45-439d-b35d-8828100860a1 · inbound

Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent cites this paper.

Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T17:37:13.927921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6e911876-1422-407c-9f65-5361d10257ef · inbound

Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets cites this paper.

Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-01T20:07:09.528204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98fecdb2-25f1-4f92-9eff-bad4329db4df · inbound

Approximate Message Passing with Random Initialization for Phase Retrieval cites this paper.

Approximate Message Passing with Random Initialization for Phase Retrieval The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T23:35:23.506017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.