Academics

Optimization on Manifolds via Graph Gaussian Processes

Time:Tues., 14:30-15:30, Jan. 23, 2024

Venue:Shuangqing Complex Building, C654

Speaker:Ruiyi Yang 杨睿逸 Princeton University

Abstract

Optimization problems on smooth manifolds are ubiquitous in science and engineering. Oftentimes the manifolds are not known analytically and only available as an unstructured point cloud, so that gradient-based methods are not directly applicable. In this talk, we shall discuss a Bayesian optimization approach, which exploits a Gaussian process over the point cloud and an acquisition function to sequentially search for the global optimizer. Regret bounds are established and several numerical examples demonstrate the effectiveness of our method.


About the speaker

Dr. Yang is a Postdoctoral Research Associate at Princeton University. He obtained his Ph.D. in Computational and Applied Mathematics at the University of Chicago. His research interests lie broadly in the mathematical foundations of data science, including inverse problems, Gaussian process computation, and nonparametric statistics.

DATEJanuary 23, 2024
SHARE
Related News
    • 0

      Gaussian Differential Privacy

      AbstractPrivacy-preserving data analysis has been put on a firm mathematical foundation since the introduction of differential privacy (DP) in 2006. This privacy definition, however, has some well-known weaknesses: notably, it does not tightly handle composition. In this talk, we propose a relaxation of DP that we term "f-DP", which has a number of appealing properties and avoids some of the di...

    • 1

      Gaussian Completely Monotone Conjecture: Progress, History and Future

      Speaker:Fan Cheng 程帆(Shanghai Jiao Tong University)Time:Tues., 9:00-10:00 am, Mar. 25, 2025Venue:Jing Zhai 105 (清华大学静斋)Online:Zoom Meeting ID: 271 534 5558Passcode: YMSCAbstract:Heat equation in mathematical physics and Gaussian channel in information theory are equivalent as the fundamental solution to heat equation is given by the heat kernel (Gaussian distribution). Gaussian c...