English

Saddle Point Optimization with Approximate Minimization Oracle

Optimization and Control 2021-04-02 v2 Neural and Evolutionary Computing

Abstract

A major approach to saddle point optimization minxmaxyf(x,y)\min_x\max_y f(x, y) is a gradient based approach as is popularized by generative adversarial networks (GANs). In contrast, we analyze an alternative approach relying only on an oracle that solves a minimization problem approximately. Our approach locates approximate solutions xx' and yy' to minxf(x,y)\min_{x'}f(x', y) and maxyf(x,y)\max_{y'}f(x, y') at a given point (x,y)(x, y) and updates (x,y)(x, y) toward these approximate solutions (x,y)(x', y') with a learning rate η\eta. On locally strong convex--concave smooth functions, we derive conditions on η\eta to exhibit linear convergence to a local saddle point, which reveals a possible shortcoming of recently developed robust adversarial reinforcement learning algorithms. We develop a heuristic approach to adapt η\eta derivative-free and implement zero-order and first-order minimization algorithms. Numerical experiments are conducted to show the tightness of the theoretical results as well as the usefulness of the η\eta adaptation mechanism.

Keywords

Cite

@article{arxiv.2103.15985,
  title  = {Saddle Point Optimization with Approximate Minimization Oracle},
  author = {Youhei Akimoto},
  journal= {arXiv preprint arXiv:2103.15985},
  year   = {2021}
}

Comments

Accepted for GECCO 2021

R2 v1 2026-06-24T00:40:17.445Z