学术报告报告主题：Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models
报 告 人：朱凌炯 副教授
报告时间：2023年12月19日（星期二）上午10:30-11:30
报告地点：37号楼3A01报告厅
邀 请 人：何志坚 教授
欢迎广大师生前往！
数学学院
2023年 12月12日
报告摘要：
Score-based generative models (SGMs) is a recent class of deep generative models with state-of-the-art performance in many applications. In this paper, we establish convergence guarantees for a general class of SGMs in 2-Wasserstein distance, assuming accurate score estimates and smooth log-concave data distribution. We specialize our result to several concrete SGMs with specific choices of forward processes modelled by stochastic differential equations, and obtain an upper bound on the iteration complexity for each model, which demonstrates the impacts of different choices of the forward processes. We also provide a lower bound when the data distribution is Gaussian. Numerically, we experiment SGMs with different forward processes, some of which are newly proposed in this paper, for unconditional image generation on CIFAR-10. We find that the experimental results are in good agreement with our theoretical predictions on the iteration complexity, and the models with our newly proposed forward processes can outperform existing models. This is based on the joint work with Xuefeng Gao and Hong M. Nguyen.
报告人介绍：
Lingjiong Zhu got his BA from University of Cambridge in 2008 and PhD from New York University in 2013. He worked at Morgan Stanley and University of Minnesota before joining the faculty at Florida State University in 2015. His research interests include applied probability, data science, financial engineering and operations research. His works have been published in many leading conferences and journals including Operations Research, Annals of Applied Probability, Finance and Stochastics, ICML, INFORMS Journal on Computing, Journal of Machine Learning Research, NeurIPS, Production and Operations Management, SIAM Journal on Financial Mathematics and Operations Research.