A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent

Eduard Gorbunov, Filip Hanzely, Peter Richtarik

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper we introduce a unified analysis of a large family of variants of proximal stochastic gradient descent (SGD) which so far have required different intuitions, convergence analyses, have different applications, and which have been developed separately in various communities. We show that our framework includes methods with and without the following tricks, and their combinations: variance reduction, importance sampling, mini-batch sampling, quantization, and coordinate sub-sampling. As a by-product, we obtain the first unified theory of SGD and randomized coordinate descent (RCD) methods, the first unified theory of variance reduced and non-variance-reduced SGD methods, and the first unified theory of quantized and nonquantized methods. A key to our approach is a parametric assumption on the iterates and stochastic gradients. In a single theorem we establish a linear convergence result under this assumption and strong-quasi convexity of the loss function. Whenever we recover an existing method as a special case, our theorem gives the best known complexity result. Our approach can be used to motivate the development of new useful methods, and offers pre-proved convergence guarantees. To illustrate the strength of our approach, we develop five new variants of SGD, and through numerical experiments demonstrate some of their properties.
Original languageEnglish (US)
Title of host publicationProceedings of the 23rdInternational Conference on Artificial Intelligence and Statistics (AISTATS) 2020, Palermo, Italy.
Number of pages10
StatePublished - 2020

Bibliographical note

KAUST Repository Item: Exported on 2021-09-02


Dive into the research topics of 'A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent'. Together they form a unique fingerprint.

Cite this