seminars:datasci:101023
Differences
This shows you the differences between two versions of the page.
| seminars:datasci:101023 [2023/09/22 20:15] – created gfu | seminars:datasci:101023 [2023/09/22 20:16] (current) – gfu | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | <WRAP centeralign>## | ||
| + | |||
| + | * Date: Tuesday, October 10, 2023 | ||
| + | * Time: 12:00pm -- 1:00pm | ||
| + | * Room: Whitney Hall 100E | ||
| + | * Speaker: Dr. Yiming Ying (SUNY University at Albany) | ||
| + | * Title: Interplay between Generalization and Optimization via Algorithmic Stability. | ||
| + | |||
| + | <WRAP center box 80%> | ||
| + | <WRAP centeralign> | ||
| + | \\ | ||
| + | In this talk, I will delve into our analysis of stochastic | ||
| + | gradient methods (SGMs), focusing on the interplay between | ||
| + | generalization and optimization within the framework of | ||
| + | statistical learning theory (SLT) and discuss their applications. | ||
| + | The core concept for our study is algorithmic stability which is a | ||
| + | notion in SLT to characterize how the output of an ML | ||
| + | algorithm changes upon a small perturbation of the training data. | ||
| + | Our theoretical studies significantly improved the existing | ||
| + | results in the convex case and led to new insights into | ||
| + | understanding the generalization of deep neural networks trained | ||
| + | by SGD in the non-convex case. I will also discuss how to derive | ||
| + | lower bounds for the convergence of existing AUC optimization | ||
| + | algorithms which further inspires a new direction for designing efficient | ||
| + | algorithms. Additionally, | ||
| + | privacy and minimax problems. | ||
| + | \\ | ||
| + | |||
| + | |||
| + | Biography of the speaker: Dr. Ying is a Professor in the Department of Mathematics | ||
| + | and Statistics at UAlbany and the founding director of the machine | ||
| + | learning lab (ML@UA). With a Ph.D. in mathematics from Zhejiang | ||
| + | University, China (2002), he completed postdoctoral training in applied | ||
| + | math and machine learning in Hong Kong and the UK. Dr. Ying's | ||
| + | research spans Statistical Learning Theory, Trustworthy Machine | ||
| + | Learning, and Optimization. He is the recipient of the SUNY | ||
| + | Chancellor’s Award for Excellence in Scholarship and Creative | ||
| + | Activities (2023) and the University of Exeter Merit Award (2012). He | ||
| + | currently holds editorial roles at Transactions on Machine Learning | ||
| + | Research, and Neurocomputing and is the managing editor for | ||
| + | Mathematical Foundation of Computing. Additionally, | ||
| + | |||
| + | </ | ||
| + | |||