Pith. sign in

REVIEW 1 cited by

Momentum-Based Variance Reduction in Non-Convex SGD

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 1905.10018 v3 pith:5FJWLCVT submitted 2019-05-24 cs.LG math.OCstat.ML

classification cs.LGmath.OCstat.ML
keywords variancereductionnon-convexsigmaachievebatchesboldsymboldescent
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Variance reduction has emerged in recent years as a strong competitor to stochastic gradient descent in non-convex problems, providing the first algorithms to improve upon the converge rate of stochastic gradient descent for finding first-order critical points. However, variance reduction techniques typically require carefully tuned learning rates and willingness to use excessively large "mega-batches" in order to achieve their improved results. We present a new algorithm, STORM, that does not require any batches and makes use of adaptive learning rates, enabling simpler implementation and less hyperparameter tuning. Our technique for removing the batches uses a variant of momentum to achieve variance reduction in non-convex optimization. On smooth losses $F$, STORM finds a point $\boldsymbol{x}$ with $\mathbb{E}[\|\nabla F(\boldsymbol{x})\|]\le O(1/\sqrt{T}+\sigma^{1/3}/T^{1/3})$ in $T$ iterations with $\sigma^2$ variance in the gradients, matching the optimal rate but without requiring knowledge of $\sigma$.

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. Muse: Representation Geometry of Muon Beyond Normalized Momentum

    cs.LG 2026-07 conditional novelty 6.0 of 10

    The matrix shape given to Muon's orthonormalization step is a genuine optimizer axis: square-ish reshapes match native Muon, skinnier reshapes interpolate toward normalized SGD with momentum.

Pith tools