Paper Citation Record · LEDGER

Partially Lazy Gradient Descent for Smoothed Online Learning

As of 14 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2601.15984.

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

pith.paper-citation-record.v1
2601.15984 v3

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T11:58:09.917048Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

14 of 14 outbound references displayed

verified exact2
verified fuzzy11
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 83e1fbeb-10ae-4c77-a766-659e7543ca97 · outbound

This paper cites Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization.

Partially Lazy Gradient Descent for Smoothed Online Learning Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:00:53.254835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ff906e46-250e-4ce1-800a-14f96c2758eb · outbound

This paper cites On sequential strategies for loss functions with memory.IEEE Transactions on Information Theory, 48(7):1947–1958.

Partially Lazy Gradient Descent for Smoothed Online Learning On sequential strategies for loss functions with memory.IEEE Transactions on Information Theory, 48(7):1947–1958

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.590087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b5c525c4-bfa6-4ee8-9783-2b6a4a47cc3d · outbound

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

Partially Lazy Gradient Descent for Smoothed Online Learning Online Learning: A Modern Introduction Using Convex Optimization

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:00:53.257541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 743b6dc9-d4d0-47b0-8530-9442e9295832 · outbound

This paper cites Output:{x t}T t=1.

Partially Lazy Gradient Descent for Smoothed Online Learning Output:{x t}T t=1

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.587642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8a3d2aee-99ae-4195-acad-4bcd55c3e5dc · outbound

This paper cites Gaussian gradients with variance 10 per coordinate.

Partially Lazy Gradient Descent for Smoothed Online Learning Gaussian gradients with variance 10 per coordinate

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.576172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 952f2fe7-571f-4577-896d-c69b5182c95e · outbound

This paper cites an unresolved cited work.

Partially Lazy Gradient Descent for Smoothed Online Learning Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-16T12:00:53.563398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 32a52ac8-2ed4-4abf-bf03-dc3863c406c8 · outbound

This paper cites Moreover, the losses within an active interval differ slightly for the learner and the comparator.

Partially Lazy Gradient Descent for Smoothed Online Learning Moreover, the losses within an active interval differ slightly for the learner and the comparator

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.565235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 55d2b1a1-d590-4e06-858d-ee40eca1f472 · outbound

This paper cites blocking argument.

Partially Lazy Gradient Descent for Smoothed Online Learning blocking argument

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.582663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f75b216e-c7d4-486a-b8fe-5436a6f9f407 · outbound

This paper cites The inequality holds because of the update rule for eachx t+1 for anyt.

Partially Lazy Gradient Descent for Smoothed Online Learning The inequality holds because of the update rule for eachx t+1 for anyt

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.585322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5bfc1e59-560d-45a8-b9f6-4875725f5ce4 · outbound

This paper cites In both cases,x t satisfies the optimality condition for minimizingh 0:t−1(x) +⟨g I t ,x⟩overX, and is therefore a valid minimizer.

Partially Lazy Gradient Descent for Smoothed Online Learning In both cases,x t satisfies the optimality condition for minimizingh 0:t−1(x) +⟨g I t ,x⟩overX, and is therefore a valid minimizer

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.577113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation aca5f870-4b84-4023-a492-a55f5c7bae11 · outbound

This paper cites Moreover, settingk=⌊c p T /PT ⌋, c >0 andσ=σ ⋆ .= p (G2+2G)T /(4RP T +R2) gives RT =O p (PT + 1)T.

Partially Lazy Gradient Descent for Smoothed Online Learning Moreover, settingk=⌊c p T /PT ⌋, c >0 andσ=σ ⋆ .= p (G2+2G)T /(4RP T +R2) gives RT =O p (PT + 1)T

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.571270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9594fcff-d276-432d-b7af-1949d32fb5c8 · outbound

This paper cites Proof.(ofTheorem.

Partially Lazy Gradient Descent for Smoothed Online Learning Proof.(ofTheorem

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.574266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a6b9fe3b-f4f4-446c-92c7-10ce1137ee2b · outbound

This paper cites unlike those results, this bound requires no additional assumptions on the domain or on the magni- tude/direction of the accumulated gradients.

Partially Lazy Gradient Descent for Smoothed Online Learning unlike those results, this bound requires no additional assumptions on the domain or on the magni- tude/direction of the accumulated gradients

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.579781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5b8a653c-a127-4367-8835-b1edbae47faa · outbound

This paper cites In thek-lazy case, the same principle applies phase by phase, with the bound expressed relative to the average within each lazy block.

Partially Lazy Gradient Descent for Smoothed Online Learning In thek-lazy case, the same principle applies phase by phase, with the bound expressed relative to the average within each lazy block

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:00:53.568258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.