REVIEW 2 cited by
Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Distributed and federated learning algorithms and techniques associated primarily with minimization problems. However, with the increase of minimax optimization and variational inequality problems in machine learning, the necessity of designing efficient distributed/federated learning approaches for these problems is becoming more apparent. In this paper, we provide a unified convergence analysis of communication-efficient local training methods for distributed variational inequality problems (VIPs). Our approach is based on a general key assumption on the stochastic estimates that allows us to propose and analyze several novel local training algorithms under a single framework for solving a class of structured non-monotone VIPs. We present the first local gradient descent-accent algorithms with provable improved communication complexity for solving distributed variational inequalities on heterogeneous data. The general algorithmic framework recovers state-of-the-art algorithms and their sharp convergence guarantees when the setting is specialized to minimization or minimax optimization problems. Finally, we demonstrate the strong performance of the proposed algorithms compared to state-of-the-art methods when solving federated minimax optimization problems.
Forward citations
Cited by 2 Pith papers
-
Complexity guarantees for risk-neutral generalized Nash equilibrium problems
A double-loop variance-reduced stochastic forward-backward-forward method computes variational equilibria in risk-neutral stochastic games, with a.s. convergence, linear rates under strong monotonicity, and O(epsilon^...
-
Distributed Online Stochastic Convex-Concave Optimization: Dynamic Regret Analyses under Single and Multiple Consensus Steps
Two distributed online stochastic mirror descent algorithms achieve dynamic saddle point regret O(max{T^{θ1}, T^{θ2}(1+V_T)}) under Bregman divergence, generalizing earlier Euclidean results to stochastic, non-Euclide...
Discussion (0). Continue with ORCID to comment.