OCLGMLFeb 15, 2024

Two trust region type algorithms for solving nonconvex-strongly concave minimax problems

arXiv:2402.09807v15 citationsh-index: 1
Originality Incremental advance
AI Analysis

This work addresses optimization challenges in minimax problems, which are incremental improvements for researchers in optimization and machine learning.

The paper tackles nonconvex-strongly concave minimax problems by proposing two trust region algorithms, MINIMAX-TR and MINIMAX-TRACE, achieving an iteration complexity of O(ε^{-1.5}) to find an (ε, √ε)-second order stationary point, matching the best known bound.

In this paper, we propose a Minimax Trust Region (MINIMAX-TR) algorithm and a Minimax Trust Region Algorithm with Contractions and Expansions(MINIMAX-TRACE) algorithm for solving nonconvex-strongly concave minimax problems. Both algorithms can find an $(ε, \sqrtε)$-second order stationary point(SSP) within $\mathcal{O}(ε^{-1.5})$ iterations, which matches the best well known iteration complexity.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes