Paper Citation Record · LEDGER

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

As of 7 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 2 inbound Pith citation observations for arXiv:2602.02431.

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

pith.paper-citation-record.v1
2602.02431 v2

Coverage vector

measured 4 of 4 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:27:36.573287Z

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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:35:21.709682Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T21:46:15.185972Z

Reference resolution

4 of 4 outbound references displayed

verified exact0
verified fuzzy0
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f5dd3e6d-78e0-4801-82aa-4424269b72a8 · outbound

This paper cites 4 cosφ− √ 3 s 2 R√ M e− M 2R2 + 2e− M 2 !# · tanφ 1 + tanφ ∥θ∥ ≤.

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning 4 cosφ− √ 3 s 2 R√ M e− M 2R2 + 2e− M 2 !# · tanφ 1 + tanφ ∥θ∥ ≤

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:36.251932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0c6aa5b-654c-41d4-8b31-341bc2d00e40 · outbound

This paper cites 67 Furthermore, we have ⟨gS, a⟩=rcosθ,⟨g S, b⟩=rcos(θ−α), which implies that D(a, b) ={cosθ·cos(θ−α)<0}.

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning 67 Furthermore, we have ⟨gS, a⟩=rcosθ,⟨g S, b⟩=rcos(θ−α), which implies that D(a, b) ={cosθ·cos(θ−α)<0}

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:36.391442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ff1f73e-4e46-48d1-bbaa-75cb11acefb3 · outbound

This paper cites Therefore, we have E[(a−b) 21{B}] =E[(⟨x, u⟩)21{B}]≥E[(u 1g1 +u 2g2)21{B}].

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning Therefore, we have E[(a−b) 21{B}] =E[(⟨x, u⟩)21{B}]≥E[(u 1g1 +u 2g2)21{B}]

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:36.573287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 707b2009-c44e-4771-a38f-93c6172cbd67 · outbound

This paper cites Alex Damian, Jason D Lee, and Joan Bruna.

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning Alex Damian, Jason D Lee, and Joan Bruna

Reference 1262

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:36.172766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 051dcdca-26ec-4585-b47d-e3111c292843 · inbound

Statistical Inference on Gradient Flows cites this paper.

Statistical Inference on Gradient Flows Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T21:46:15.187582Z

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 b5c581aa-e286-4c48-9fe2-29a3cd0c3319 · inbound

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

Approximate Message Passing with Random Initialization for Phase Retrieval Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T23:35:21.709682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.