activity
20242026
collaborators

5 papers

cs.LG2026

Function graph transformers universally approximate operators between function spaces

Takashi Furuya, David Mis, Ivan Dokmanić +2

We study the approximation of nonlinear operators between function spaces by transformers. Our approach is to lift functions to measures supported on their graphs and leverage a re…

math.OC2026

Training Infinitely Deep and Wide Transformers

Raphaël Barboni, Maarten V. de Hoop, Takashi Furuya +1

Transformers have become the dominant architecture in modern machine learning, yet the theoretical understanding of their training dynamics remains limited. This paper develops a r…

cs.CL2025

Transformers through the lens of support-preserving maps between measures

Takashi Furuya, Maarten V. de Hoop, Matti Lassas

Transformers are deep architectures that define ``in-context maps'' which enable predicting new tokens based on a given set of tokens (such as a prompt in NLP applications or a set…

cs.LG2024

Can neural operators always be continuously discretized?

Takashi Furuya, Michael Puthawala, Maarten V. de Hoop +1

We consider the problem of discretization of neural operators between Hilbert spaces in a general framework including skip connections. We focus on bijective neural operators throu…

cs.CL2024

Transformers are Universal In-context Learners

Takashi Furuya, Maarten V. de Hoop, Gabriel Peyré

Transformers are deep architectures that define "in-context mappings" which enable predicting new tokens based on a given set of tokens (such as a prompt in NLP applications or a s…