Zac Cranko

f-GANs in an Information Geometric Nutshell

2017 · arXiv (Cornell University)

Nowozin \textit{et al} showed last year how to extend the GAN \textit{principle} to all $f$-divergences. The approach is elegant but falls short of a full description of the supervised game, and says little about the …

Monge blunts Bayes: Hardness Results for Adversarial Training

2018 · arXiv (Cornell University)

The last few years have seen a staggering number of empirical studies of the robustness of neural networks in a model of adversarial perturbations of their inputs. Most rely on an adversary which carries out …