SILO: Differential Privacy versus Robustness: Black-Box Reductions and Efficient Algorithms

I’ll discuss connections between robustness to adversarial corruption and differential privacy in high-dimensional statistical estimation problems; highlights include (1) a black-box reduction from privacy to robustness and (2) the first computationally-efficient algorithms for learning high-dimensional Gaussians privately with nearly-optimal sample complexity (and robustness).

Based on joint works with Kristian Georgiev, Gautam Kamath, Mahbod Majid, and Shyam Narayanan

Bio: 

Sam Hopkins is an Assistant Professor at MIT, in the Theory of Computing group in the Department of Electrical Engineering and Computer Science, where he holds the Jamieson Career Development Chair. Previously, Sam was a Miller fellow in the theory group at UC Berkeley, hosted by Prasad Raghavendra and Luca Trevisan. Before that, he received his PhD at Cornell, advised by David Steurer.