26–30 Jun 2023
ECT*
Europe/Rome timezone

Continuous flows and transfer learning

27 Jun 2023, 15:30
25m
Aula Renzo Leonardi (ECT*)

Aula Renzo Leonardi

ECT*

Strada delle Tabarelle 286, I-38123 Villazzano (Trento)

Speaker

Mathis Gerdes (University of Amsterdam)

Description

We explore continuous flows as generative models, focusing on their architectural flexibility in implementing equivariance, and test them on the $φ^4$ theory. Using this setup, we show how a machine-learning approach enables transfer between lattice sizes and allows us to learn for a continuous range of theory parameters at once. Investigating the sample efficiency of training, we find that the expressivity of continuous flows may justify their higher numerical cost due to integration.

Primary authors

Mathis Gerdes (University of Amsterdam) Pim de Haan

Co-authors

Presentation materials