Skip to yearly menu bar Skip to main content


The Galerkin method beats Graph-Based Approaches for Spectral Algorithms

Vivien Cabannes · Francis Bach

MR1 & MR2 - Number 144
[ ]
Sat 4 May 6 a.m. PDT — 8:30 a.m. PDT


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.

Live content is unavailable. Log in and register to view live content