27th Conference of the International Linear Algebra Society (ILAS 2026)

Operator Learning via Learned Differential Operators

May 21, 2026, 2:25 PM

25m

McBryde Hall 113 (Virginia Tech)

Minisymposium Talk Theoretical Advances in Operator Learning Theoretical Advances in Operator Learning

Speaker

Juan Felipe Osorio Ramirez (University of Washington)

Description

We present an alternative perspective on operator learning for problems in which the operator is implicitly defined by a partial differential equation. Rather than learning the solution operator directly as a high-dimensional mapping, we propose to first learn the underlying PDE operator as a local differential operator and then numerically invert it to evaluate the associated solution operator.