SMS scnews item created by Catherine Meister at Mon 23 Feb 2026 1021
Type: Seminar
Distribution: World
Expiry: 16 Mar 2026
Calendar1: 26 Feb 2026 1300-1400
CalLoc1: SMRI Seminar Room (A12 Macleay Room 301)
Auth: cmeister@10.136.117.223 (cmei0631) in SMS-SAML

SMRI Seminar: Zech

Learning Theory for Neural Operators

Jakob Zech, University of Heidelberg

SMRI Seminar, Thursday 26th February 2026, 1 pm – 2 pm, SMRI Seminar Room (A12 Macleay Room 301)

Abstract:In this talk, we present results on the approximability and data requirements necessary to learn surrogates of nonlinear mappings between infinite-dimensional spaces. Such surrogate models have a wide range of applications and can be used in uncertainty quantification and parameter estimation problems in fields such as classical mechanics, fluid mechanics, electrodynamics, and earth sciences. Our analysis shows that, for certain neural network architectures, empirical risk minimization based on noisy input-output pairs can overcome the curse of dimensionality. Additionally, we provide a numerical comparison to other approaches including classical constructive methods.

For seminar updates, see our What's On Calendar. Please join us after the seminar for the SMRI afternoon tea, every Thursday at 2 pm on the SMRI Terrace.