Pith. sign in

REVIEW 1 cited by

Asymptotic Time-Uniform Inference for Parameters in Averaged Stochastic Approximation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.15057 v1 pith:4WY44U3Y submitted 2024-10-19 stat.ML cs.LGstat.ME

classification stat.MLcs.LGstat.ME
keywords asymptoticapproximationaveragedcoverageguaranteesinferenceparametersstochastic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study time-uniform statistical inference for parameters in stochastic approximation (SA), which encompasses a bunch of applications in optimization and machine learning. To that end, we analyze the almost-sure convergence rates of the averaged iterates to a scaled sum of Gaussians in both linear and nonlinear SA problems. We then construct three types of asymptotic confidence sequences that are valid uniformly across all times with coverage guarantees, in an asymptotic sense that the starting time is sufficiently large. These coverage guarantees remain valid if the unknown covariance matrix is replaced by its plug-in estimator, and we conduct experiments to validate our methodology.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization

    stat.ML 2026-04 unverdicted novelty 6.0 of 10

    Q-learning with PD2Z/LD2Z step sizes admits sharp non-asymptotic bounds, a tail Polyak–Ruppert CLT, and a time-uniform Gaussian approximation, establishing a best-of-both-worlds rate-and-bias tradeoff.

Pith tools