hep-lat · 2605.17326 Copy arXiv ID · May 17, 2026 Save Noise scheduling and linear dynamics in diffusion models on Lie groups Authors: Javad Komijani
Organizations: Institute for Theoretical Physics, ETH Zurich, 8093 Zurich, Switzerland
Abstract We investigate the role of the noise schedule in diffusion processes on Lie groups, with particular emphasis on applications to lattice gauge theory. We show that a specific noise schedule leads to a linear decay of the expectation value of the Wilson action as a function of diffusion time. We compare this with Euclidean diffusion models, where such behavior requires an explicitly designed drift term, while in the Lie-group setting it arises naturally.
Explore similar work May 7, 2026 · Javad Komijani, Marina K. Marinkovic, Lara Turgut Effective Field Theory Monte Carlo
Jun 25, 2026 · Octavio Vega, Aida X. El-Khadra Effective Field Theory
May 21, 2026 · Seo Taek Kong, Weina Wang, R. Srikant Fisher Information Optimal Control
May 7, 2026 · hep-lat J/K move · Enter open · S save
Javad Komijani, Marina K. Marinkovic, Lara Turgut
Institute for Theoretical Physics, ETH Zurich, 8093 Zurich, Switzerland
Implicit score matching provides a computationally efficient approach for training diffusion models and generating high-quality samples from complex distributions. In this work, we develop a score-matching framework for SU(N) lattice gauge theories, which can be extended to other Lie groups. We apply the method to SU(3) gauge configurations with the Wilson gauge action in two and four dimensions and assess the quality of the generated samples by comparison with Hybrid Monte Carlo (HMC) simulations. We show that the diffusion models can be successfully trained and applied for sampling the Wilson gauge action. For large values of inverse coupling, accurate reverse-time integration requires predictor-corrector schemes, for which we introduce a corrector based on Hamiltonian molecular dynamics. While the corrector significantly improves sampling quality, it also increases the computational cost. We outline several strategies for improving sampling efficiency.