NeurIPS 2020

Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function


Meta Review

The paper introduces a single-loop stochastic algorithm for solving a special class of nonconvex-concave minimax problems that achieves best-known complexity bound. The rebuttal addressed most of the reviewers' concerns on the algorithmic justification, although some concern remains in terms of the special structure. I recommend acceptance. However, please consider revising the paper to address R1 and R3 's remarks, in particular: - Adjust the title to reflect the special structure instead of overclaim the contribution; - Elaborate the desirable property of single-loop algorithm over existing methods; - Add detailed comparisons to prior work including prox-linear algorithms for compositional problems and recent algorithms for general nonconvex-concave minimax problems.