← Search

Michael Anthony Puthawala

2 accepted papers

2024

Can neural operators always be continuously discretized?

NeurIPS 2024poster

In this work we consider the problem of discretization of neural operators in a general setting. Using category theory, we give a no-go theorem that shows that diffeomorphisms between Hilbert spaces may not admit any continuous approximations by diffeomorphisms on finite spaces, even if the discreti…

Cited by 0SourcePDFScholar
2023

Globally injective and bijective neural operators

NeurIPS 2023poster

Recently there has been great interest in operator learning, where networks learn operators between function spaces from an essentially infinite-dimensional perspective. In this work we present results for when the operators learned by these networks are injective and surjective. As a warmup, we com…

Cited by 14SourcePDFScholar