ABSTRACT: In this talk I will describe how some popular ML algorithms can play an important role in solving challenging problems in Computational Physics. This will include the use of Variationally Mimetic Operator Networks as fast, differentiable surrogates for complex differential operators, the use of Generative Adversarial Networks in solving stochastic inverse problems, and the use of Graph Laplacians for constructing multi-fidelity models. I will present illustrative examples, and in some cases, discuss theoretical estimates for the performance of these algorithms.

BIOSKETCH: Assad Oberai is the Hughes Professor of Aerospace and Mechanical Engineering in the Viterbi School of Engineering. He leads the Computation and Data Driven Discovery (CD3) group which designs, implements and applies data- and physics-based models and algorithms to solve problems in engineering and science. Problems such as better detection, diagnosis and care of diseases like cancer, understanding the role of mechanics and physics in medicine and biology, modeling the evolution of multi-physics and multiscale systems, and reduced-order models for aerospace and mechanical systems. He has authored more than 100 articles in archival journals on these topics. He is on the board of academic editors for three journals.

Assad is a Fellow of the ASME, the AIMBE, and the USACM. He was awarded the Thomas J.R. Hughes Young Investigator Award for his contributions to Applied Mechanics by the ASME in 2007. He is a recipient of the National Science Foundation Career award in 2005 and the Department of Energy Early Career award in 2004.