NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:192
Title:Reducing Noise in GAN Training with Variance Reduced Extragradient

The paper is certainly of interest to the NeurIPS community and very well written. However, the title is misleading and should be changed as for GAN the objective functions are not convex (or strongly convex). However, the result of this paper is only valid when such strong assumptions are made. Moreover, the counterexample provided by the authors does not even work under their own assumptions.