Towards Understanding the Convergence Behavior of Newton-Type Methods for Structured Convex Optimization Problems¶
SO, Man Cho Anthony
Associate Professor
The Chinese University of Hong Kong
Abstract: Recently, there has been a growing interest in applying Newton-type methods to solve structured convex optimization problems that arise in machine learning and
statistics. A major obstacle to the design and analysis of such methods is that many
problems of interest are neither strongly convex nor smooth. In this talk, we will
present some design techniques for overcoming such obstacle and report some
recent progress on analyzing the convergence rates of the resulting Newton-type
methods using error bounds. We will also discuss some directions for further study.
Bio: Anthony Man-Cho So received his BSE degree in Computer Science from Princeton
University with minors in Applied and Computational Mathematics, Engineering
and Management Systems, and German Language and Culture. He then received
his MSc degree in Computer Science and his PhD degree in Computer Science with
a PhD minor in Mathematics from Stanford University. Dr. So joined The Chinese
University of Hong Kong (CUHK) in 2007. He currently serves as Assistant Dean of
the Faculty of Engineering and is an Associate Professor in the Department of
Systems Engineering and Engineering Management. His recent research focuses on
the interplay between optimization theory and various areas of algorithm design,
such as computational geometry, machine learning, signal processing,
bioinformatics, and algorithmic game theory.
Dr. So currently serves on the editorial boards of IEEE Transactions on Signal
Processing, Journal of Global Optimization, Optimization Methods and Software,
and SIAM Journal on Optimization. He has also served on the editorial board of
Mathematics of Operations Research. He received the 2015 IEEE Signal Processing
Society Signal Processing Magazine Best Paper Award, the 2014 IEEE
Communications Society Asia-Pacific Outstanding Paper Award, the 2010 Institute
for Operations Research and the Management Sciences (INFORMS) Optimization Society
Optimization Prize for Young Researchers, and the 2010 CUHK Young Researcher Award.