DeepAI AI Chat
Log In Sign Up

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

by   Eduard Gorbunov, et al.
King Abdullah University of Science and Technology
Moscow Institute of Physics and Technology

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 non-quantized 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.


Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization

We present a unified theorem for the convergence analysis of stochastic ...

Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods

Stochastic Gradient Descent-Ascent (SGDA) is one of the most prominent a...

Linearly Converging Error Compensated SGD

In this paper, we propose a unified analysis of variants of distributed ...

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

We propose a remarkably general variance-reduced method suitable for sol...

A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization

In this paper, we study the performance of a large family of SGD variant...

SEGA: Variance Reduction via Gradient Sketching

We propose a randomized first order optimization method--SEGA (SkEtched ...

Variance Reduction with Sparse Gradients

Variance reduction methods such as SVRG and SpiderBoost use a mixture of...