![Computational Complexity of Statistical Inference_hi-res logo](/sites/default/files/styles/workshop_banner_sm_1x/public/2023-03/Computational%20Complexity%20of%20Statistical%20Inference_hi-res.jpg?h=ccd3d9f7&itok=qCiIzWU5)
Abstract
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