Speaker
Description
Quantum Field Theory (QFT) and modern Machine Learning (ML) share deep structural analogies, from path integrals and renormalization to latent spaces and marginalization. With its solid theoretical foundation, QFT offers a powerful lens to interpret global behaviors in ML that remain poorly understood. This talk explores the interplay between QFT and ML in both directions.
In QFT, the only systematically-improvable, first-principles approach is Lattice QFT, based on evaluating the path integral using MCMC algorithms which remains the state-of-the-art. Recently, architectures based on Normalizing Flows (NF) have been proposed to enhance or even replace these methods. We will show how ML can help address the long-standing signal-to-noise degradation problem in Lattice QFT by combining NF with stochastic automatic differentiation.
Conversely, we discuss how QFT provides a controlled environment to explore core ML concepts. In particular, we present a generative stochastic autoencoder trained to perform a Super Resolution task on field configurations, where notions like depth, latent structure, and resolution enhancement emerge in a physically meaningful context.
| Broad physics domain | Stochastic numerical methods for quantum field theory on the lattice |
|---|---|
| AI/ML technique(s) to be presented | Stochasting autoencoders, Super Resolution networks, Gauge-equivariant (continuous) normalizing flows, (neural ODEs) |
