PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities

by   Zhuqing Liu, et al.

Recently, min-max optimization problems have received increasing attention due to their wide range of applications in machine learning (ML). However, most existing min-max solution techniques are either single-machine or distributed algorithms coordinated by a central server. In this paper, we focus on the decentralized min-max optimization for learning with domain constraints, where multiple agents collectively solve a nonconvex-strongly-concave min-max saddle point problem without coordination from any server. Decentralized min-max optimization problems with domain constraints underpins many important ML applications, including multi-agent ML fairness assurance, and policy evaluations in multi-agent reinforcement learning. We propose an algorithm called PRECISION (proximal gradient-tracking and stochastic recursive variance reduction) that enjoys a convergence rate of O(1/T), where T is the maximum number of iterations. To further reduce sample complexity, we propose PRECISION^+ with an adaptive batch size technique. We show that the fast O(1/T) convergence of PRECISION and PRECISION^+ to an ϵ-stationary point imply O(ϵ^-2) communication complexity and O(m√(n)ϵ^-2) sample complexity, where m is the number of agents and n is the size of dataset at each agent. To our knowledge, this is the first work that achieves O(ϵ^-2) in both sample and communication complexities in decentralized min-max learning with domain constraints. Our experiments also corroborate the theoretical results.


page 1

page 2

page 3

page 4


INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks

In recent years, decentralized bilevel optimization problems have receiv...

Enhanced First and Zeroth Order Variance Reduced Algorithms for Min-Max Optimization

Min-max optimization captures many important machine learning problems s...

Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks

Bilevel optimization have gained growing interests, with numerous applic...

DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization

Decentralized bilevel optimization has received increasing attention rec...

Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning

This paper is the first to propose a generic min-max bilevel multi-objec...

GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning

Decentralized nonconvex optimization has received increasing attention i...

Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity

The finite-time convergence of off-policy TD learning has been comprehen...

Please sign up or login with your details

Forgot password? Click here to reset