主 講 人： Florida State University, 朱凌炯 教授
報告時間：2025年7月7日 上午10:30-11:30
報告地點：覽秀樓105學術報告廳
報告摘要: Sampling is a powerful tool in modern-day applications in machine learning and generative AI. We will discuss two examples: Langevin algorithms and score-based generative models. Both are stochastic algorithms that can be used to solve large-scale problems in machine learning and generative AI respectively. In particular, we will provide non-asymptotic Wasserstein convergence guarantees and iteration complexities. Numerical results and applications will also be discussed.
主講人簡介：朱凌炯，博士，Florida State University教授和Thinking Machines杰出學者，博士生導師。2008年本科畢業于University of Cambridge。2013年博士畢業于New York University，師從S.R.S. Varadhan。 現任Probability in the Engineering and Informational Sciences編委。主要研究興趣有應用概率，數據科學，金融工程及運籌學，在Annals of Applied Probability, Bernoulli, Finance and Stochastics, ICML, INFORMS Journal on Computing, Journal of Machine Learning Research, NeurIPS, Operations Research, Production and Operations Management, SIAM Journal on Financial Mathematics, Stochastic Processes and their Applications, Review of Economics and Statistics等雜志發表數十篇論文。曾多次主持 NSF項目。曾于2013年獲得NYU Courant Institute的Kurt O. Friedrichs最佳博士論文獎，2022年獲得FSU的發展學者獎，2023年獲得FSU的研究生導師獎，MSOM Society的MSOM iFORM SIG最佳論文獎。
