10 papers
Diffusion Models for Sampling Near Criticality in Lattice Field Theories
Yang-yang Tan, Gert Aarts, Diaa E. Habibi +2
We investigate generative diffusion models as denoising samplers for two- and three-dimensional lattice theory across the symmetric, near-critical, and broken phases. Valida…
Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theory
Gert Aarts, Diaa E. Habibi, Andreas Ipp +5
We demonstrate that gauge equivariant diffusion models can accurately model the physics of non-Abelian lattice gauge theory using the Metropolis-adjusted annealed Langevin algorith…
Physics-Conditioned Diffusion Models for Lattice Gauge Theory
Qianteng Zhu, Gert Aarts, Wei Wang +2
We develop diffusion models for simulating lattice gauge theories, where stochastic quantization is explicitly incorporated as a physical condition for sampling. We demonstrate the…
Combining complex Langevin dynamics with score-based and energy-based diffusion models
Gert Aarts, Diaa E. Habibi, Lingxiao Wang +1
Theories with a sign problem due to a complex action or Boltzmann weight can sometimes be numerically solved using a stochastic process in the complexified configuration space. How…
On learning higher-order cumulants in diffusion models
Gert Aarts, Diaa E. Habibi, Lingxiao Wang +1
To analyse how diffusion models learn correlations beyond Gaussian ones, we study the behaviour of higher-order cumulants, or connected n-point functions, under both the forward an…
Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
Gert Aarts, Kenji Fukushima, Tetsuo Hatsuda +4
The integration of deep learning techniques and physics-driven designs is reforming the way we address inverse problems, in which accurate physical properties are extracted from co…