Searcharxiv⌕ Search

arXiv subjects

Diaa E. Habibi

Publications and source records attributed to Diaa E. Habibi.

7 recordsLinked to original sources

Generative diffusion models for lattice field theory

Generative diffusion models offer a new route to ensemble generation in lattice field theory. The backward, or denoising, process underlying these models is a stochastic process with a learned, time-dependent drift, which leads to a clear connection with stochastic quantisation. After reviewing this correspondence, I turn to theories with a sign problem. There the complex Boltzmann weight obstructs direct sampling, but complex Langevin dynamics can sometimes evade the sign problem by generating configurations on a complexified manifold, distributed according to a real and semi-positive distribution. This distribution is not known in closed form. I discuss how this distribution can be learned from complex Langevin data using score-based and, in particular, energy-based diffusion models. The latter give direct access to the unnormalised distribution itself, which can subsequently be used as the weight in a standard Markov chain Monte Carlo simulation. Results are shown for a simple quartic model with a complex action.

hep-lat↗

Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theory: Analytical Foundations and Numerical Scaling Tests

Gauge-equivariant diffusion models can be used to generate ensembles of field configurations in non-abelian lattice gauge theories. Previously, we demonstrated the feasibility of modeling these theories by combining L-CNN-based diffusion models with the Metropolis-adjusted annealed Langevin algorithm (MAALA). Here we focus on the underlying analytical framework. In particular, we present a rigorous derivation of the reverse-time stochastic differential equation on the group manifold, discuss the gauge invariance of the denoising loss function, and provide extensive numerical benchmarks regarding the scaling behavior with respect to the lattice volume and the inverse coupling $β$. Full analytical expressions for arbitrarily sized Wilson loops and the topological charge susceptibility during the forward process are given as well.

hep-lat↗

Diffusion Models for Sampling Near Criticality in Lattice Field Theories

We investigate generative diffusion models as denoising samplers for two- and three-dimensional lattice $ϕ^4$ theory across the symmetric, near-critical, and broken phases. Validated against ensembles generated by Fourier-accelerated HMC combined with Wolff cluster updates, the reverse-SDE sampler reproduces scalar observables and the momentum-space propagator $G(|k|)$, with residual bias concentrated in the zero-mode and, in three dimensions, the action density. We introduce two local diagnostics and an HMC-referenced effective sample size (ESS), which probe the learned drift directly, through a Metropolis-adjusted Langevin acceptance rate, and through observable-level bias and variance. Exploiting a fully convolutional architecture with weights shared across different volumes ($V=L^D$), we show that cross-volume training transfers to unseen sizes, matching or slightly improving in-distribution training in the two-dimensional symmetric and broken phases. A three-dimensional model trained on $L \in \{4, 8, 16, 32\}$ reproduces the propagator and most scalar observables at the unseen lattice size $L = 64$ across the phase diagram, with the residual susceptibility excess in the broken phase as the main exception, and improves several critical observables relative to in-distribution $L = 64$ training. This establishes cross-volume generalization as a viable mechanism for large-volume sampling, and the score learned from many cheap small-lattice configurations transfers to the target volume without retraining.

hep-lat↗

Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theory

We demonstrate that gauge equivariant diffusion models can accurately model the physics of non-Abelian lattice gauge theory using the Metropolis-adjusted annealed Langevin algorithm (MAALA), as exemplified by computations in two-dimensional U(2) and SU(2) gauge theories. Our network architecture is based on lattice gauge equivariant convolutional neural networks (L-CNNs), which respect local and global symmetries on the lattice. Models are trained on a single ensemble generated using a traditional Monte Carlo method. By studying Wilson loops of various size as well as the topological susceptibility, we find that the diffusion approach generalizes remarkably well to larger inverse couplings and lattice sizes with negligible loss of accuracy while retaining moderately high acceptance rates.

hep-lat↗

Combining complex Langevin dynamics with score-based and energy-based diffusion models

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. However, the probability distribution effectively sampled by this complex Langevin process is not known a priori and notoriously hard to understand. In generative AI, diffusion models can learn distributions, or their log derivatives, from data. We explore the ability of diffusion models to learn the distributions sampled by a complex Langevin process, comparing score-based and energy-based diffusion models, and speculate about possible applications.

hep-lat↗

On learning higher-order cumulants in diffusion models

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 and backward process. We derive explicit expressions for the moment- and cumulant-generating functionals, in terms of the distribution of the initial data and properties of forward process. It is shown analytically that during the forward process higher-order cumulants are conserved in models without a drift, such as the variance-expanding scheme, and that therefore the endpoint of the forward process maintains nontrivial correlations. We demonstrate that since these correlations are encoded in the score function, higher-order cumulants are learnt in the backward process, also when starting from a normal prior. We confirm our analytical results in an exactly solvable toy model with nonzero cumulants and in scalar lattice field theory.

hep-lat↗

Diffusion models learn distributions generated by complex Langevin dynamics

The probability distribution effectively sampled by a complex Langevin process for theories with a sign problem is not known a priori and notoriously hard to understand. Diffusion models, a class of generative AI, can learn distributions from data. In this contribution, we explore the ability of diffusion models to learn the distributions created by a complex Langevin process.

hep-lat↗