Skip to yearly menu bar Skip to main content


Poster

Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization

Siqi Zhang · Yifan Hu · Liang Zhang · Niao He

MR1 & MR2 - Number 165
[ ]
Fri 3 May 8 a.m. PDT — 8:30 a.m. PDT

Abstract: This paper studies the generalization performance of algorithms for solving nonconvex-(strongly)-concave (NC-SC/NC-C) stochastic minimax optimization measured by the stationarity of primal functions. We first establish algorithm-agnostic generalization bounds via uniform convergence between the empirical minimax problem and the population minimax problem. The sample complexities for achieving $\epsilon$-generalization are $\tilde{\mathcal{O}}(d\kappa^2\epsilon^{-2})$ and $\tilde{\mathcal{O}}(d\epsilon^{-4})$ for NC-SC and NC-C settings, respectively, where $d$ is the dimension of the primal variable and $\kappa$ is the condition number. We further study the algorithm-dependent generalization bounds via stability arguments of algorithms. In particular, we introduce a novel stability notion for minimax problems and build a connection between stability and generalization. As a result, we establish algorithm-dependent generalization bounds for stochastic gradient descent ascent (SGDA) and the more general sampling-determined algorithms (SDA).

Live content is unavailable. Log in and register to view live content