Return to Colloquia & Seminar listing
Optimization on Manifolds via Graph Gaussian Processes
Mathematics of Data & Decisions| Speaker: | Ruiyi Yang, Princeton University |
| Related Webpage: | https://ruiyiyang.github.io/ |
| Location: | Zoom |
| Start time: | Tue, Feb 6 2024, 3:10PM |
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.