Papers › Momentum-Based Variance Reduction in Non-Convex SGD

Momentum-Based Variance Reduction in Non-Convex SGD

24 May 2019NeurIPS 2019 12arXiv:1905.10018archive 2025-07-28

Ashok Cutkosky, Francesco Orabona

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 x with 𝔼[∇F(x)]≤O(1/√(T)+σ^(1/3)/T^(1/3)) in T iterations with σ² variance in the gradients, matching the optimal rate but without requiring knowledge of σ.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

google-research/google-research officialmentioned in papertf report
duanzhiihao/PyTorch_OLoptim mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections