Pith. sign in

REVIEW 1 cited by

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods

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 1905.11266 v2 pith:SZAUBTQV submitted 2019-05-27 math.OC cs.LGcs.NAmath.NA

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods

classification math.OC cs.LGcs.NAmath.NA
keywords methodmethodslargecasesknownnumberspecialstochastic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose a remarkably general variance-reduced method suitable for solving regularized empirical risk minimization problems with either a large number of training examples, or a large model dimension, or both. In special cases, our method reduces to several known and previously thought to be unrelated methods, such as {\tt SAGA}, {\tt LSVRG}, {\tt JacSketch}, {\tt SEGA} and {\tt ISEGA}, and their arbitrary sampling and proximal generalizations. However, we also highlight a large number of new specific algorithms with interesting properties. We provide a single theorem establishing linear convergence of the method under smoothness and quasi strong convexity assumptions. With this theorem we recover best-known and sometimes improved rates for known methods arising in special cases. As a by-product, we provide the first unified method and theory for stochastic gradient and stochastic coordinate descent type methods.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization

    cs.LG 2025-09 conditional novelty 3.0

    A PhD dissertation showing unified compression theory, personalized accelerated local training, and pruning methods that reduce communication costs in federated learning and maintain accuracy in LLM pruning.