Accurate Sampling from Diffusion Models

arXiv:2609.29902 · hep-lat, cond-mat.dis-nn, cs.LG · Submitted 2026-09-24 · Read on arXiv

hep-lat, cond-mat.dis-nn, cs.LG

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Diffusion Model — 32× in this paper · explained in 8 episodes
• Diffusion Process — 24× in this paper · explained in 2 episodes
• Diffusion Models — 20× in this paper · explained in 6 episodes
• Sequential Monte Carlo — 11× in this paper
• Benchmark — 5× in this paper · explained in 2 episodes
• Normalizing Flow — 5× in this paper · explained in 3 episodes
• Normalizing Flows — 5× in this paper · explained in 4 episodes
• Loss Function — 4× in this paper · explained in 2 episodes
• Diffusion Processes — 3× in this paper · explained in 2 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Activation Function — 1× in this paper · explained in 1 episode
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Langevin Dynamics — 1× in this paper · explained in 2 episodes
• Metropolis-adjusted Langevin Algorithm — 1× in this paper
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Sequential Monte Carlo (SMC) — 1× in this paper · explained in 2 episodes
• While Markov Chain Monte Carlo — 1× in this paper
• alpha — 1× in this paper · explained in 1 episode

Sources

• Critical slowing down and error analysis in lattice QCD simulations
• Aspects of scaling and scalability for flow-based sampling of lattice QCD
• Advances in machine-learning-based sampling motivated by lattice quantum chromodynamics
• Regressive and generative neural networks for scalar field theory
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Equivariant flow-based sampling for lattice gauge theory
• Sampling using $SU(N)$ gauge equivariant flows
• Introduction to Normalizing Flows for Lattice Field Theory
• Fourier-Flow model generating Feynman paths
• Flow-based sampling for lattice field theories
• Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows
• Sampling the lattice Nambu-Goto string using Continuous Normalizing Flows
• Stochastic normalizing flows as non-equilibrium transformations
• Efficient Modelling of Trivializing Maps for Lattice $\phi^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Generative models for scalar field theories: how to deal with poor scaling?
• Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories
• AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning
• Diffusion Models as Stochastic Quantization in Lattice Field Theory

Related papers

• MORE Thermal Gauge Theories at Finite theta and mu from Real-Time Quantum Simulation
• Sampling the Schwinger Model with Gauge-Equivariant Diffusion
• Confinement, String Breaking, and Hadronization in the Compact Abelian Higgs Model
• Continuum limit of a qubit-regularized SU(3) lattice gauge theory on a plaquette chain