New perspective from Blackwell's comparisons of experiments on generative adversarial networks and differential privacy

We bring the tools from Blackwell's seminal result on comparing two stochastic experiments, to shine new lights on two modern applications of great interest: generative adversarial networks (GAN) and differential privacy (DP). Binary hypothesis testing is at the center of both applications, and we propose new data processing inequalities that allows us to discover new algorithms, provide sharper analyses, and provide simpler proofs. In the case of GAN, this leads to a new architecture to handle one of the major challenges in GAN known as "mode collapse' the lack of diversity in the samples generated by the learned generators. The hypothesis testing view of GAN allows us to analyze the new architecture and show that it encourages generators with no mode collapse. In the case of DP, we answer one of the most fundamental questions in differential privacy: how much privacy is lost after k queries to the database? The hypothesis testing view of DP gives the complete solution: the privacy degradation guarantee is true for every differentially private mechanism and, further, we demonstrate a sequence of privacy mechanisms that do degrade in the characterized manner, exactly. For this talk, I will assume no prior background on either GAN or DP.
Sewoong Oh is an Assistant Professor of Industrial and Enterprise Systems Engineering at UIUC. He received his PhD from the department of Electrical Engineering at Stanford University. Following his PhD, he worked as a postdoctoral researcher at Laboratory for Information and Decision Systems (LIDS) at MIT. He was co-awarded the Kenneth C. Sevcik outstanding student paper award at the Sigmetrics 2010, the best paper award at the SIGMETRICS 2015, and NSF CAREER award in 2016.