Feizi Receives NSF CAREER Award to Advance Generative Models in Machine Learning

A University of Maryland expert in machine learning has won a National Science Foundation (NSF) Faculty Early Career Development (CAREER) award for a project intended to improve machine learning capabilities using generative models.

Soheil Feizi, an assistant professor of computer science, is principal investigator of the NSF award, expected to total $589,000 over five years.

The funding supports Feizi’s efforts to develop a comprehensive and fundamental understanding of the intertwined statistical and computational aspects of modern generative models such as Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs).

Generative machine learning models provide a statistical understanding of data and play an important role in the success of modern machine learning in various application domains like computer vision, natural language processing, computational biology, and more.

Building on the success of deep learning, recent advances in modern generative models hold great promise in revolutionizing various learning methods, Feizi says. Despite this progress, the understanding of some fundamental aspects of these models—often required for characterizing their performance guarantees—is still in its infancy.

Feizi hopes to make critical advances in proper formulations of generative models for high dimensional distributions, characterizing statistical limits of these models, and developing efficient computational approaches for solving optimization problems involved during their training

The NSF-funded work will involve leveraging tools and concepts from information theory, statistics and optimization, he says.

“This cross-disciplinary project broadens the scope of the prior knowledge on the interplay between information theory and machine learning,” says Feizi, who has an appointment in the University of Maryland Institute for Advanced Computer Studies and is a core faculty member in the University of Maryland Center for Machine Learning. “We expect that it will create a tightly connected loop between theory, algorithms and applications in data science.”

The project also includes a comprehensive plan to integrate the research results into an inclusive, diverse and cross-disciplinary educational program at the high school, undergraduate and graduate levels.

Feizi has already been active in improving diversity and inclusion in data science and machine learning. He helped establish a Rising Stars in Machine Learning program that brought up-and-coming female researchers to the UMD campus to present their work and interact with other machine learning experts.

Feizi received his doctorate in electrical engineering and computer science from MIT in 2016.

“CAREER: Information-Theoretic and Statistical Foundations of Generative Models” is supported by NSF grant #1942230 from the NSF’s Division of Computing and Communication Foundations.

PI: Soheil Feizi, assistant professor of computer science with appointments in the University of Maryland Institute for Advanced Computer Studies (UMIACS) and the University of Maryland Center for Machine Learning.

About the CAREER award: The Faculty Early Career Development (CAREER) Program is an NSF activity that offers the foundation’s most prestigious awards in support of junior faculty who exemplify the role of teacher-scholars through outstanding research, excellent education and the integration of education and research within the context of the mission of their organization.