Saved in:
Bibliographic Details
Main Authors: Cabannes, Vivien, Bach, Francis
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.00742
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916136655781888
author Cabannes, Vivien
Bach, Francis
author_facet Cabannes, Vivien
Bach, Francis
contents Historically, the machine learning community has derived spectral decompositions from graph-based approaches. We break with this approach and prove the statistical and computational superiority of the Galerkin method, which consists in restricting the study to a small set of test functions. In particular, we introduce implementation tricks to deal with differential operators in large dimensions with structured kernels. Finally, we extend on the core principles beyond our approach to apply them to non-linear spaces of functions, such as the ones parameterized by deep neural networks, through loss-based optimization procedures.
format Preprint
id arxiv_https___arxiv_org_abs_2306_00742
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Galerkin method beats Graph-Based Approaches for Spectral Algorithms
Cabannes, Vivien
Bach, Francis
Machine Learning
Artificial Intelligence
Historically, the machine learning community has derived spectral decompositions from graph-based approaches. We break with this approach and prove the statistical and computational superiority of the Galerkin method, which consists in restricting the study to a small set of test functions. In particular, we introduce implementation tricks to deal with differential operators in large dimensions with structured kernels. Finally, we extend on the core principles beyond our approach to apply them to non-linear spaces of functions, such as the ones parameterized by deep neural networks, through loss-based optimization procedures.
title The Galerkin method beats Graph-Based Approaches for Spectral Algorithms
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2306.00742