CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence

by   Kun Huang, et al.

In this paper, we consider solving the distributed optimization problem over a multi-agent network under the communication restricted setting. We study a compressed decentralized stochastic gradient method, termed β€œcompressed exact diffusion with adaptive stepsizes (CEDAS)", and show the method asymptotically achieves comparable convergence rate as centralized SGD for both smooth strongly convex objective functions and smooth nonconvex objective functions under unbiased compression operators. In particular, to our knowledge, CEDAS enjoys so far the shortest transient time (with respect to the graph specifics) for achieving the convergence rate of centralized SGD, which behaves as π’ͺ(nC^3/(1-Ξ»_2)^2) under smooth strongly convex objective functions, and π’ͺ(n^3C^6/(1-Ξ»_2)^4) under smooth nonconvex objective functions, where (1-Ξ»_2) denotes the spectral gap of the mixing matrix, and C>0 is the compression-related parameter. Numerical experiments further demonstrate the effectiveness of the proposed algorithm.


page 1

page 2

page 3

page 4

βˆ™ 05/11/2021

Improving the Transient Times for Distributed Stochastic Gradient Methods

We consider the distributed optimization problem where n agents each pos...
βˆ™ 02/01/2022

DoCoM-SGT: Doubly Compressed Momentum-assisted Stochastic Gradient Tracking Algorithm for Communication Efficient Decentralized Learning

This paper proposes the Doubly Compressed Momentum-assisted Stochastic G...
βˆ™ 06/21/2023

Distributed Random Reshuffling Methods with Improved Convergence

This paper proposes two distributed random reshuffling methods, namely G...
βˆ™ 10/28/2022

Secure Distributed Optimization Under Gradient Attacks

In this paper, we study secure distributed optimization against arbitrar...
βˆ™ 08/28/2022

Asynchronous Training Schemes in Distributed Learning with Time Delay

In the context of distributed deep learning, the issue of stale weights ...
βˆ™ 02/11/2022

Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach

Decentralized sparsity learning has attracted a significant amount of at...
βˆ™ 07/26/2021

Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs

In this work, we consider the decentralized optimization problem in whic...

Please sign up or login with your details

Forgot password? Click here to reset