← All plenary speakers

Alex Townsend

Associate Professor of Mathematics, Cornell University

A Mathematical Guide to Operator Learning

Abstract

A fundamental challenge in modern scientific computing is learning an operator from finite data. In this talk, we offer a mathematical guide to operator learning, drawing a distinction between passive and active observation models and revealing the crucial role this choice plays in sample efficiency. We explore how the nature of the underlying partial differential equation, i.e., elliptic, parabolic, or hyperbolic, governs the difficulty of learning the associated solution operator, and we present recent learning theory that quantifies the number of queries needed for accurate recovery. Diffusive systems, as we shall see, are forgiving; wave-like systems are not. Along the way, we reflect on what it means to learn in infinite dimensions and how mathematical structure can be exploited to tame the curse of dimensionality.

Bio

Alex Townsend is an Associate Professor of Mathematics at Cornell University, working on numerical analysis, scientific computing, and machine learning. His research focuses on the development of efficient algorithms for high-dimensional problems, with particular emphasis on spectral methods, low-rank approximation, and operator learning. He is the recipient of several awards, including the Leslie Fox Prize in Numerical Analysis, the SIAM Activity Group on Linear Algebra Prize, the SIAM Activity Group on Computational Science and Engineering Prize, SIAM SIGEST, a Simons Fellowship in Mathematics, and Cornell University's Stephen H. Weiss Fellowship for excellence in teaching.