时   间：2026-06-10 13:00 - 2026-06-10 15:00

地   点：普陀校区理科大楼A1514室

报告人：Rong Ma   哈佛大学助理教授

主持人：项冬冬   华东师范大学

摘   要：

Learning and representing low-dimensional structures from noisy, high-dimensional data is a cornerstone of modern data science. Stochastic neighbor embedding algorithms, a family of nonlinear dimensionality reduction and data visualization methods, with t-SNE and UMAP as two leading examples, have become very popular in recent years. Yet despite their wide applications, these methods remain subject to points of debate, including limited theoretical understanding, ambiguous interpretations, and sensitivity to tuning parameters. In this talk, I will present our recent efforts to decipher and improve these nonlinear embedding approaches. Our key results include a rigorous theoretical framework that uncovers the intrinsic mechanisms, large-sample limits, and fundamental principles underlying these algorithms; a set of theory-informed practical guidelines for their principled use in trustworthy biological discovery; and a collection of new algorithms that address current limitations and improve performance in areas such as bias reduction and stability. Throughout the talk, I will highlight how these advances not only deepen our theoretical understanding but also open new avenues for scientific discovery.

报告人简介：

Professor Rong Ma is an Assistant Professor of Biostatistics at the Harvard T.H. Chan School of Public Health, a position he has held since August 2023. He earned his B.S. in Statistics from Nankai University, followed by an M.S. in Statistics & Data Science from the University of Wisconsin–Madison, and completed his Ph.D. in Biostatistics with a minor in mathematics at the University of Pennsylvania in 2021, where he was co-advised by Professors Hongzhe Li and T. Tony Cai. He subsequently undertook postdoctoral training at Stanford University, working with Professor David Donoho. His research centers on the intersection of statistics and biomedical data science, with a core focus on establishing rigorous theoretical foundations for modern nonlinear dimension reduction and visualization methods such as t-SNE and UMAP, while also developing principled and interpretable machine learning approaches for single-cell integrative genomics and multiomics. He is the recipient of several prestigious awards, including the IMS Lawrence D. Brown Ph.D. Student Award, the Saul Winegrad Award for Outstanding Dissertation from the University of Pennsylvania, and a SIAM Travel Award.