Applications of Gaussian Stein’s Identity to Non-Convex Optimization and Sampling
Date/Time:11 Sep 2019 16:00Venue: S17 #05-11 SR5Speaker: Krishna Balasubramanian, UC DavisApplications of Gaussian Stein’s Identity to Non-Convex Optimization and SamplingOptimization and sampling are arguably the computational backbones of Frequentist and Bayesian statistics respectively. In this talk the use of Gaussian Stein’s identity for performing stochastic Zeroth-Order (ZO) non-convex optimization and sampling will be discussed. Specifically, we consider the case when the function (or density) under consideration is not available to us analytically, rather we are able to only obtain noisy evaluations. Using Gaussian Stein’s identity, techniques for estimating the gradient and Hessian of a function (or density) will be introduced. Based on this, the following algorithms and the corresponding theoretical results will be discussed: (i) ZO stochastic gradient method in high-dimensions (ii) ZO Newton’s method for escaping saddle points (iii) ZO Euler and Ozaki discretized (Kinetic) Langevin Monte Carlo sampling.Add to calendar:
