Decentralized Stochastic Variance Reduced Extragradient Method

02/01/2022
by   Luo Luo, et al.
0

This paper studies decentralized convex-concave minimax optimization problems of the form min_xmax_y f(x,y) ≜1/m∑_i=1^m f_i(x,y), where m is the number of agents and each local function can be written as f_i(x,y)=1/n∑_j=1^n f_i,j(x,y). We propose a novel decentralized optimization algorithm, called multi-consensus stochastic variance reduced extragradient, which achieves the best known stochastic first-order oracle (SFO) complexity for this problem. Specifically, each agent requires 𝒪((n+κ√(n))log(1/ε)) SFO calls for strongly-convex-strongly-concave problem and 𝒪((n+√(n)L/ε)log(1/ε)) SFO call for general convex-concave problem to achieve ε-accurate solution in expectation, where κ is the condition number and L is the smoothness parameter. The numerical experiments show the proposed method performs better than baselines.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset