15th Shannon Memorial Lecture; Understanding Generative Adversarial Networks

David Tse, Stanford University

 

Date: 2017-11-17
Time: 2p Lecture 3p recptn
Location: Calit2 Auditorium Atkinson Hall, UC San Diego

Guest Speaker: David Tse, Stanford University
Professor


Host: Center for Memory and Recording Research


DESCRIPTION/ABSTRACT:

Stanford professor David Tse, recipient of the 2017 Claude E. Shannon Award, will deliver the 15th annual Shannon Memorial Lecture hosted by CMRR, the Qualcomm Institute and its Information Theory and Applications Center (ITA).

Claude Shannon invented information theory to understand the fundamental limits of communication. Since then, it has revolutionized the communication field. The core of information theory is an approach to research based on finding the simplest model to study a problem. Although conceived and cultivated in the context of communication, this approach to research has much broader applicability. In this talk, we illustrate this using our recent work on Generative Adversarial Networks (GANs).

GANs is a novel approach to the age-old problem of learning a probabilistic model from data. Learning is achieved by setting up a game between a generator whose goal is to generate fake data that are close to the real data, and a discriminator whose goal is to distinguish between the real and fake data. Even though many increasingly complex GANs architectures have been proposed recently, several basic issues remain unanswered: 1) What is a general way of specifying the loss function of GANs? 2) What is the limiting solution of a GAN as the amount of data increases? 3) What is the generalization ability of a GAN?

We answer these questions in the simplest setting of the problem. In the process, a connection is drawn between GANs, optimal transport theory, and rate-distortion theory.


SPEAKER BIO:

David Tse received the BASc degree in systems design engineering from University of Waterloo in 1989, and the MS and PhD degrees in electrical engineering from MIT in 1991 and '94, respectively. From 1994-95, he was a postdoctoral member of the technical staff at AT&T Bell Laboratories. From 1995 to 2014, he was on the faculty of UC Berkeley, and is currently the Thomas Kailath and Guanghan Xu Professor at Stanford University. Tse is the recipient of the 2017 Claude E. Shannon Award. Previously he received an NSF CAREER Award in 1998, the Erlang Prize from the INFORMS Applied Probability Society in 2000, and a Gilbreth Lectureship from the National Academy of Engineering in 2012. Tse received multiple best-paper awards, including from the Information Theory Society (in 2003), IEEE Communications Society and Information Theory Society Joint Paper Awards in 2000, 2013 and 2015, the Signal Processing Society (2012), and the IEEE Communications Society Stephen O. Rice Prize in 2013. For his contributions to education, Tse received the Outstanding Teaching Award from UC Berkeley's EECS department in 2008, and the Frederick Emmons Terman Award from the American Society for Engineering Education in 2009. He is a coauthor with Pramod Viswanath of the text, Fundamental of Wireless Communication, which has been used in over 60 institutions around the world. Tse is also the inventor of the proportional-fair scheduling algorithm used in all third and fourth-generation cellular systems, serving 2.7 billion people around the world.

MORE INFORMATION:

Please contact ivilla@ucsd.edu if you have any questions or concerns.