Diffusion Models as Stochastic Quantization in Lattice Field Theory

Abstract

In this work, we establish a direct connection between generative diffusion models (DMs) and stochastic quantization (SQ). The DM is realized by approximating the reversal of a stochastic process dictated by the Langevin equation, generating samples from a prior distribution to effectively mimic the target distribution. Using numerical simulations, we demonstrate that the DM can serve as a global sampler for generating quantum lattice field configurations in two-dimensional ${\varphi }^4$ theory. We demonstrate that DMs can notably reduce autocorrelation times in the Markov chain, especially in the critical region where standard Markov Chain Monte-Carlo (MCMC) algorithms experience critical slowing down. The findings can potentially inspire further advancements in lattice field theory simulations, in particular in cases where it is expensive to generate large ensembles.

arXiv comment30 pages, 15 figures. The open code can be found at https://github.com/Anguswlx/DMasSQ

References in corpus (41)

• MCMC using Hamiltonian dynamics
• Diffusion Models in Vision: A Survey
• Trivializing maps, the Wilson flow and the HMC algorithm
• Monte Carlo errors with less errors
• Critical slowing down and error analysis in lattice QCD simulations
• The Complex Langevin method: When can it be trusted?
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Complex Langevin: Etiology and Diagnostics of its Main Problem
• Simulating full QCD at nonzero density using the complex Langevin equation
• Equivariant flow-based sampling for lattice gauge theory
• Can stochastic quantization evade the sign problem? -- the relativistic Bose gas at finite chemical potential
• Lattice simulations of real-time quantum fields
• Gauge cooling in complex Langevin for QCD with heavy quarks
• Finite-density lattice QCD and sign problem: current status and open problems
• The argument for justification of the complex Langevin method and the condition for correct convergence
• Introductory lectures on lattice QCD at nonzero baryon number
• Stochastic quantization at finite chemical potential
• Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
• Regressive and generative neural networks for scalar field theory
• Score-based Generative Models for Calorimeter Shower Simulation
• Complex Langevin dynamics and zeroes of the fermion determinant
• Exploring QCD matter in extreme conditions with Machine Learning
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• Complex Langevin and boundary terms
• Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimation
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models
• Gauge-equivariant flow models for sampling in lattice field theories with pseudofermions
• pyerrors: a python framework for error analysis of Monte Carlo data
• Mapping distinct phase transitions to a neural network
• Flow-based sampling in the lattice Schwinger model at criticality
• Learning Lattice Quantum Field Theories with Equivariant Continuous Flows
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Complex Langevin simulations and the QCD phase diagram: Recent developments
• Learning Trivializing Gradient Flows for Lattice Gauge Theories
• Fourier-Flow model generating Feynman paths
• Phase transition of four-dimensional lattice ${\varphi }^4$ theory with tensor renormalization group
• Towards learning optimized kernels for complex Langevin
• Stable solvers for real-time Complex Langevin
• Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems
• Cooling Stochastic Quantization with colored noise

Cited by in corpus (16)

• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Machine learning a fixed point action for SU(3) gauge theory with a gauge equivariant convolutional neural network
• On learning higher-order cumulants in diffusion models
• Stochastic quantization and diffusion models
• Scaling of Stochastic Normalizing Flows in $\mathrm{SU}(3)$ lattice gauge theory
• Ultra fast, event-by-event heavy-ion simulations for next generation experiments
• Toward a foundation model for heavy-ion collision experiments based on point-cloud diffusion
• Scaling flow-based approaches for topology sampling in $\mathrm{SU}(3)$ gauge theory
• The neural networks with tensor weights and emergent fermionic Wick rules in the large-width limit
• Reconstruction of Gravitational Form Factors using Generative Machine Learning
• Diffusion Models for SU(2) Lattice Gauge Theory in Two Dimensions
• Journey from the Wilson exact RG towards the Wegner-Morris Fokker-Planck RG and the Carosso field-coarsening via Langevin stochastic processes
• Variational Neural Network Approach to QFT in the Field Basis
• Efficient identification of critical regions via Flow Matching-based Monte Carlo initialization
• Combining complex Langevin dynamics with score-based and energy-based diffusion models
• Group-Equivariant Diffusion Models for Lattice Field Theory