Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:3FSEUGPVrecord.jsonopen to challenge →
read the original abstract
We propose a novel single-loop decentralized algorithm called DGDA-VR for solving the stochastic nonconvex strongly-concave minimax problem over a connected network of $M$ agents. By using stochastic first-order oracles to estimate the local gradients, we prove that our algorithm finds an $\epsilon$-accurate solution with $\mathcal{O}(\epsilon^{-3})$ sample complexity and $\mathcal{O}(\epsilon^{-2})$ communication complexity, both of which are optimal and match the lower bounds for this class of problems. Unlike competitors, our algorithm does not require multiple communications for the convergence results to hold, making it applicable to a broader computational environment setting. To the best of our knowledge, this is the first such algorithm to jointly optimize the sample and communication complexities for the problem considered here.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
A Stochastic GDA Method With Backtracking For Solving Nonconvex Concave Minimax Problems
SGDA-B is the first backtracking-enabled stochastic GDA algorithm for nonconvex-concave minimax problems that achieves the best known complexity bounds among methods agnostic to L, μ, and σ².
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.