Operator learning without the adjoint

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Boullé, Nicolas, Halikias, Diana, Otto, Samuel E., Townsend, Alex
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912127411814400
author Boullé, Nicolas
Halikias, Diana
Otto, Samuel E.
Townsend, Alex
author_facet Boullé, Nicolas
Halikias, Diana
Otto, Samuel E.
Townsend, Alex
contents There is a mystery at the heart of operator learning: how can one recover a non-self-adjoint operator from data without probing the adjoint? Current practical approaches suggest that one can accurately recover an operator while only using data generated by the forward action of the operator without access to the adjoint. However, naively, it seems essential to sample the action of the adjoint. In this paper, we partially explain this mystery by proving that without querying the adjoint, one can approximate a family of non-self-adjoint infinite-dimensional compact operators via projection onto a Fourier basis. We then apply the result to recovering Green's functions of elliptic partial differential operators and derive an adjoint-free sample complexity bound. While existing theory justifies low sample complexity in operator learning, ours is the first adjoint-free analysis that attempts to close the gap between theory and practice.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17739
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Operator learning without the adjoint
Boullé, Nicolas
Halikias, Diana
Otto, Samuel E.
Townsend, Alex
Numerical Analysis
Artificial Intelligence
Machine Learning
There is a mystery at the heart of operator learning: how can one recover a non-self-adjoint operator from data without probing the adjoint? Current practical approaches suggest that one can accurately recover an operator while only using data generated by the forward action of the operator without access to the adjoint. However, naively, it seems essential to sample the action of the adjoint. In this paper, we partially explain this mystery by proving that without querying the adjoint, one can approximate a family of non-self-adjoint infinite-dimensional compact operators via projection onto a Fourier basis. We then apply the result to recovering Green's functions of elliptic partial differential operators and derive an adjoint-free sample complexity bound. While existing theory justifies low sample complexity in operator learning, ours is the first adjoint-free analysis that attempts to close the gap between theory and practice.
title Operator learning without the adjoint
topic Numerical Analysis
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2401.17739