Speaker: Dr. Ying ZHANG 张莹 博士

Time: 15:00-15:45, 28 May 2026 (Tue.)

Venue: T2-102

Abstract

Motivated by applications in deep learning, where the global Lipschitz continuity condition is often not satisfied, we examine the problem of sampling from distributions with super-linearly growing log-gradients. We propose a novel tamed Langevin dynamics-based algorithm, called kTULA, to solve the aforementioned sampling problem, and provide a theoretical guarantee for its performance. More precisely, we establish a non-asymptotic convergence bound in Kullback-Leibler (KL) divergence with the best-known rate of convergence equal to 2−ϵ, ϵ>0, which significantly improves relevant results in existing literature. This enables us to obtain an improved non-asymptotic error bound in Wasserstein-2 distance, which can be used to further derive a non-asymptotic guarantee for kTULA to solve the associated optimization problems. To illustrate the applicability of kTULA, we apply the proposed algorithm to the problem of sampling from a high-dimensional double-well potential distribution and to an optimization problem involving a neural network. We show that our main results can be used to provide theoretical guarantees for the performance of kTULA.

About the Speaker

Dr. Ying Zhang is an Assistant Professor in the Financial Technology Thrust at the Hong Kong University of Science and Technology (Guangzhou). She obtained her PhD degree from the University of Edinburgh and has previously worked as a postdoctoral researcher at Nanyang Technological University. Her research interests lie in the design and analysis of machine learning algorithms, as well as their applications in data science and finance. Her research papers have been published in leading journals including Mathematics of Operations Research, IMA Journal of Numerical Analysis, Bernoulli, and SIAM Journal on Mathematics of Data Science.