Dear Colleagues,
This is a reminder that SLDS September webinar, presented by Professor Krishna Balasubramanian, is at 3:00pm this Wednesday. The topic is optimization-based analysis of sampling algorithms. Hope to see you then.
Title: Optimization-based analysis of sampling algorithms
Speakers: Dr. Krishna Balasubramanian, Department of Statistics, University of California, Davis
Date and Time: September 27, 2022, 3:00 to 4:30 pm Eastern Time
Registration Link: ASA SLDS Webinar Registration Link [eventbrite.com]
Abstract: This talk will be about recent advances in the complexity of sampling, motivated by from the theory of (non-convex) optimization. First, a framework for establishing the iteration complexity of sampling of the Langevin Monte Carlo (LMC) when sampling from a non-log-concave target density will be discussed. Next, deterministic algorithms for sampling, like Stein Variational Gradient Analysis (SVGD) will be introduced. A framework for comparing such deterministic methods to classical MCMC methods will be introduced. Furthermore, connections to variational inference will be illustrated.
Presenter: Krishna Balasubramanian is currently an Associate Professor in the Department of Statistics at the University of California, Davis, where he also holds affiliations with the Graduate Group in Applied Mathematics, the Center for Data Science and Artificial Intelligence Research (CeDAR), and the TETRAPODS Institute of Data Science. He served as a visiting scientist at the Simons Institute for the Theory of Computing, UC Berkeley, during the fall semesters of 2021 and 2022. Krishna earned his Ph.D. in Computer Science from the Georgia Institute of Technology and conducted postdoctoral research at both Princeton University and the University of Wisconsin-Madison. His research interests are centered around the intersection of machine learning, optimization, and statistics. Krishna's research has been supported by a Facebook Ph.D. fellowship, as well as grants from CeDAR and the National Science Foundation. He actively contributes to the academic community as an associate editor for the Journal of Machine Learning Research and as a (senior) area chair for conferences like the International Conference on Machine Learning (ICML), Advances in Neural Information Processing Systems (NeurIPS), and the Conference on Learning Theory (COLT).
------------------------------
Zhihua Su, PhD
Associate Professor
Department of Statistics
University of Florida
zhihuasu@stat.ufl.edu------------------------------