EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization

Abstract

In distributed or federated optimization and learning, communication between the different computing units is often the bottleneck, and gradient compression is a widely used technique for reducing the number of bits sent within each communication round of iterative methods. There are two classes of compression operators and separate algorithms making use of them. In the case of unbiased random compressors with bounded variance (e.g., rand-k), the DIANA algorithm of Mishchenko et al. [2019], which implements a variance reduction technique for handling the variance introduced by compression, is the current state of the art. In the case of biased and contractive compressors (e.g., top-k), the EF21 algorithm of Richt\'arik et al. [2021], which implements an error-feedback mechanism for handling the error introduced by compression, is the current state of the art. These two classes of compression schemes and algorithms are distinct, with different analyses and proof techniques. In this paper, we unify them into a single framework and propose a new algorithm, recovering DIANA and EF21 as particular cases. We prove linear convergence under certain conditions. Our general approach works with a new, larger class of compressors, which includes unbiased and biased compressors as particular cases, and has two parameters, the bias and the variance. These gives a finer control and allows us to inherit the best of the two worlds: biased compressors, whose good performance in practice is recognized, can be used. And independent randomness at the compressors allows to mitigate the effects of compression, with the convergence rate improving when the number of parallel workers is large. This is the first time that an algorithm with all these features is proposed. Our approach takes a step towards better understanding of two so-far distinct worlds of communication-efficient distributed learning.