:::

[2018-03-06] Dr. Yen-Huan Li, École polytechnique fédérale de Lausanne, “Bridging the theory and practice: A unified statistical and optimization perspective”

專題討論演講公告
張貼人:Seminar專用帳號2公告日期:2018-03-02

Title: Bridging the theory and practice: A unified statistical and optimization perspective
Date: 2018-03-06 13:00-14:00
Location: R210, CSIE
Speaker: Yen-Huan Li, École polytechnique fédérale de Lausanne
Hosted by: Prof.Chih-Jen Lin

Abstract:

Despite many exciting empirical successes in data science, there are significant gaps between theory and inspired-by-theory practices. For example, the standard lasso (\ell_1-penalized least squares regression) is not appropriate for variable selection in non-linear statistical models; uniformly random sampling suggested by theory is not adopted in practical compressive medical imaging; the standard bounded gradient/ curvature condition in convex optimization just does not hold in some crucial applications. In this talk, I will present how we addressed these gaps—rigorously—via identifying more general conditions on the problem settings, or reformulating the problem under Vapnik's transduction framework.


 

Biography:

Yen-Huan Li received the B.S.E. degree in electrical engineering in 2008, and M.S. degree in communication engineering in 2010, both from National Taiwan University, Taipei, Taiwan. He is currently a candidate for the Ph.D. degree in computer science at École polytechnique fédérale de Lausanne, Switzerland. From

2010 to 2011, he served the mandatory military service in Taiwan, and from 2011 to 2012, he was a Research Assistant at Academia Sinica, Taipei, Taiwan. His research interests include machine learning, high-dimensional statistics, convex optimization, and quantum information theory.

最後修改時間:2018-03-02 AM 11:27

cron web_use_log