“Generative Adversarial Networks: Formulation, Design and Computation”

Location: LTS Auditorium, 8080 Greenmead Drive

Speaker:
Soheil Feizi
Assistant professor, Department of Computer Science and UMIACS

Abstract:
Learning a probability model from data is a fundamental problem in machine learning and statistics. A classical approach to this problem is to fit (approximately) an explicit probability model to the training data via a maximum likelihood estimation.

Building off the success of deep learning, however, there has been another approach to this problem using Generative Adversarial Networks (GANs). GANs view this problem as a game between two sets of functions: a generator whose goal is to generate realistic fake samples and a discriminator whose goal is to distinguish between the real and fake samples.

In this talk, I will explain challenges that we face in formulation, design and computation of GANs. Leveraging a connection between supervised and unsupervised learning, I will then elaborate how we can overcome these issues by proposing a model-based view to GANs.

Speaker Bio:
Soheil Feizi is an assistant professor in the Department of Computer Science at the University of Maryland, College Park. He is also affiliated with the University of Maryland Institute for Advanced Computer Studies (UMIACS).

Feizi’s research interests are in the area of machine learning and statistical inference.

Before joining UMD, he was a postdoctoral research scholar at Stanford University.

Feizi received his doctorate in electrical engineering and computer science (EECS) with a minor degree in mathematics from MIT.

He also completed a M.Sc. in EECS at MIT, where he received the Ernst Guillemin award for his thesis, as well as the Jacobs Presidential Fellowship and the EECS Great Educators Fellowship.

Additionally, Feizi received the best student award at Sharif University of Technology, where he obtained his B.Sc.