Holder： Zhu Weichen（The University of Hong Kong）
Time：2026-03-09 14:00-15:00
Location：WANG Xuan Lecture Theater，Zhi Hua Building-101
Abstract:
Deep Gaussian processes have attracted lots of research attention in the recent years. However, it suffers the same, if not more severe, bottleneck as the (one-layer) Gaussian processes due to cubic computational complexity of evaluating a high-dimensional joint Gaussian density. In this paper, we propose Deep Vecchia Gaussian processes, a highly non-trivia marriage between Deep Gaussian process and (one-layer) Vecchia Gaussian processes. The proposed method puts Vecchia Gaussian processes on the layer-wise mappings rather than the intermediate states of the training, which cleverly circumvents the random parent sets problem that prevails in literature. The proposed Deep Vecchia Gaussian process, when served as prior for statistical problems, results valid Bayesian methods with automatic uncertainty quantification, whereas enjoying scalable computational complexity and minimax optimality over a wide range of composite functions.
About the Speaker:
Yian Ma is an assistant professor at the Halıcıoğlu Data Science Institute, UC San Diego. Prior to UCSD, he spent a year as a visiting faculty at Google Research. Before that, he was a post-doctoral fellow at UC Berkeley, hosted by Mike Jordan. Yian completed his Ph.D. at University of Washington. His current research primarily revolves around scalable inference methods for credible machine learning, with application to time series data and sequential decision making tasks. He has received the Facebook research award, the Stein fellowship, and the best paper awards at the Neurips and ICML workshops.
Your participation is warmly welcomed!
欢迎扫码关注北大统计科学中心公众号，了解更多讲座信息!
