Pith. sign in

REVIEW 1 cited by

Anytime Tail Averaging

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1902.05083 v2 pith:GAORORXP submitted 2019-02-13 cs.LG stat.APstat.ML

Nicolas Le Roux This is my paper · ORCID
classification cs.LGstat.APstat.ML
keywords averagingaveragememorytailcosteverytechniquesaccess
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Tail averaging consists in averaging the last examples in a stream. Common techniques either have a memory requirement which grows with the number of samples to average, are not available at every timestep or do not accomodate growing windows. We propose two techniques with a low constant memory cost that perform tail averaging with access to the average at every time step. We also show how one can improve the accuracy of that average at the cost of increased memory consumption.

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. AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent

    cs.LG 2025-05 conditional novelty 6.0 of 10

    AutoSGD runs three parallel SGD streams at nearby learning rates, uses paired noisy objective estimates to pick the winner, and is claimed to converge with little user tuning.

Pith tools