Accelerated methods for composite non-bilinear saddle point problem

Abstract

Based on G. Lan's accelerated gradient sliding and general relation between the smoothness and strong convexity parameters of function under Legendre transformation we show that under rather general conditions the best known bounds for bilinear convex-concave smooth composite saddle point problem keep true for or non-bilinear convex-concave smooth composite saddle point problem. Moreover, we describe situations when the bounds differ and explain the nature of the difference.

28 pages, in Russian

References in corpus (2)

• A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
• Searching equillibriums in large transport networks

Cited by in corpus (7)

• Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization
• Solving smooth min-min and min-max problems by mixed oracle algorithms
• Accelerated meta-algorithm for convex optimization
• Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization
• Output Perturbation for Differentially Private Convex Optimization: Faster and More General
• Convex-Concave Min-Max Stackelberg Games
• Minimax Optimization: The Case of Convex-Submodular