[Seminar] Non-convex Optimization for Data Science: Models, Algorithms, and Applications
Monday, February 28, 2022
11:00 am - 12:00 pm
Speaker
Songtao
Lu
Research
Scientist
IBM
Thomas
J.
Watson
Research
Center
Location
Virtual:
Online
via
Zoom*
*Microsoft
365
@cougarnet.uh.edu
authentication
required
to
join
via
Zoom
Abstract
We live in an era of data explosion. The rapid advances in sensor, communication, and storage technologies have made data acquisition more ubiquitous than at any time in the past. Making sense of data of such a scale is expected to bring ground-breaking advances across many industries and disciplines. However, to effectively handle data of such scale and complexity, and to better extract information from quintillions of bytes of data for inference, learning and decision-making, increasingly complex mathematical models are needed. These models are often highly non-convex, unstructured, and can have millions or even billions of variables, making existing methods no longer applicable.
In this talk, I will present a few recent works that design accurate, robust, and scalable algorithms for solving non-convex big data problems. My focus will be given to discussing the theoretical properties of a class of gradient-based algorithms for solving a popular family of structured non-convex min-max problems. I will also showcase the practical performance of these algorithms in applications such as adversarial learning, multi-view learning, and distributed/decentralized training. Finally, I will briefly introduce some extensions of our framework to other emerging problems, such as safe reinforcement learning (RL), multi-agent RL, etc.
About the Speaker
Songtao Lu is currently a research scientist with the mathematics of artificial intelligence (AI) group at the IBM Thomas J. Watson Research Center, Yorktown Heights. He obtained his doctoral degree in electrical engineering from Iowa State University in 2018. He was a post-doctoral associate with the department of electrical and computer engineering at the University of Minnesota Twin Cities from 2018 to 2019, and an AI resident at the IBM Thomas J. Watson Research Center from 2019 to 2020. Dr. Lu is a recipient of the research excellence award from the graduate college at Iowa State University, IBM research accomplishment award, and ICML and AISTATS travel awards. His recent works have been published at multiple top-tier AI and machine learning conferences, including ICML, NeurIPS, AAAI, ICLR, AISTATS, etc. His primary research interests lie in data science, machine learning, AI, and optimization.
