skip to Main Content

University of Hawaii

Electrical Engineering

Block Structured Nonconvex Optimization for Machine Learning and Information Processing

Date: 2019-03-08           Add to Google Calendar
Time: 10:30am - 11:30am
Location: Holmes 389
Speaker: Dr. Songtao Lu


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 quintillion of bytes of data for inference, learning and decision-making, increasingly complex mathematical models are needed. These models are often highly nonconvex, unstructured, and can have millions or even billions of variables, making existing solution methods no longer applicable.

In this talk, I will present a few recent works that design accurate, scalable, and robust algorithms for solving non-convex big data problems. Our focus will be given to discussing theoretical and practical properties of a class of gradient-based algorithms for solving a popular family of "block-structured" non-convex problems. We will also showcase the practical performance of these algorithms in applications such as topic modeling, resource allocation, distributionally robust learning, and decentralized training neural networks. Finally, I will briefly introduce the possible extension of our framework to other emerging problems such as distributed reinforcement learning and adversarial learning problems.


Songtao Lu is currently a Post-Doctoral Associate with the Department of Electrical and Computer Engineering at the University of Minnesota Twin Cities, Minneapolis. His primary research interests include optimization, machine learning, wireless communications, and signal processing. He received his Ph.D. degree in Electrical and Computer Engineering from Iowa State University in 2018. He was a recipient of the Graduate and Professional Student Senate Research Award from Iowa State University in 2015, the Research Excellence Award from the Graduate College of Iowa State University in 2017, and the Student Travel Award from the International Conference on Artificial Intelligence and Statistics in 2017.