Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models

Abstract

In this work, we demonstrate that applying deep generative machine learning models for lattice field theory is a promising route for solving problems where Markov Chain Monte Carlo (MCMC) methods are problematic. More specifically, we show that generative models can be used to estimate the absolute value of the free energy, which is in contrast to existing MCMC-based methods which are limited to only estimate free energy differences. We demonstrate the effectiveness of the proposed method for two-dimensional ${\varphi }^4$ theory and compare it to MCMC-based methods in detailed numerical experiments.

arXiv comment8 figures

References in corpus (32)

• Auto-Encoding Variational Bayes
• A nonequilibrium equality for free energy differences
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Equilibrium free energy differences from nonequilibrium measurements: a master equation approach
• NICE: Non-linear Independent Components Estimation
• Variational Inference with Normalizing Flows
• Heavy Ion Collisions: The Big Picture, and the Big Questions
• Monte Carlo errors with less errors
• Normalizing Flows for Probabilistic Modeling and Inference
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Equivariant flow-based sampling for lattice gauge theory
• The QCD equation of state from the lattice
• A study of the 't Hooft loop in SU(2) Yang-Mills theory
• Sampling using $SU(N)$ gauge equivariant flows
• Asymptotically unbiased estimation of physical observables with neural samplers
• Thermodynamics of SU(3) Gauge Theory from Gradient Flow
• Deep Learning and AdS/CFT
• Deep Learning and Holographic QCD
• Equation of state of the SU($3$) Yang-Mills theory: a precise determination from a moving frame
• Machine learning action parameters in lattice quantum chromodynamics
• AdS/CFT as a deep Boltzmann machine
• Deep Learning and AdS/QCD
• QCD thermodynamics from lattice calculations with non-equilibrium methods: The SU(3) equation of state
• Mapping distinct phase transitions to a neural network
• Tensor renormalization group approach to four-dimensional complex ${\varphi }^4$ theory at finite density
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Equation of state of a relativistic theory from a moving frame
• With missing title of the paper. Overrelaxation Algorithm for coupled Gauge-Higgs systems
• Towards reduction of autocorrelation in HMC by machine learning
• Quantum fields as deep learning
• Comment on "Solving Statistical Mechanics Using VANs": Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling

Cited by in corpus (57)

• Machine Learning in Nuclear Physics
• Sampling using $SU(N)$ gauge equivariant flows
• Exploring QCD matter in extreme conditions with Machine Learning
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Flow-based sampling for fermionic lattice field theories
• 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
• Normalizing flows for atomic solids
• Stochastic normalizing flows as non-equilibrium transformations
• Quantum field-theoretic machine learning
• Flow-based sampling in the lattice Schwinger model at criticality
• Learning Lattice Quantum Field Theories with Equivariant Continuous Flows
• Learning Trivializing Gradient Flows for Lattice Gauge Theories
• Machine Learning of consistent thermodynamic models using automatic differentiation
• Normalizing Flows and the Real-Time Sign Problem
• Diffusion Models as Stochastic Quantization in Lattice Field Theory
• Deep Variational Free Energy Approach to Dense Hydrogen
• Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse
• Fourier-Flow model generating Feynman paths
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• Generalization capabilities of translationally equivariant neural networks
• Flow-based density of states for complex actions
• Sampling the lattice Nambu-Goto string using Continuous Normalizing Flows
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
• Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
• Machine learning spectral functions in lattice QCD
• Hierarchical autoregressive neural networks for statistical systems
• Numerical determination of the width and shape of the effective string using Stochastic Normalizing Flows
• Efficient mapping of phase diagrams with conditional Boltzmann Generators
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Generative Neural Samplers for the Quantum Heisenberg Chain
• On learning higher-order cumulants in diffusion models
• Parallel Tempered Metadynamics: Overcoming potential barriers without surfing or tunneling
• Scaling of Stochastic Normalizing Flows in $\mathrm{SU}(3)$ lattice gauge theory
• Adaptive Monte Carlo augmented with normalizing flows
• Machine learning phases of an Abelian gauge theory
• Training normalizing flows with computationally intensive target probability distributions
• Generative models for sampling of lattice field theories
• Rényi entanglement entropy of spin chain with Generative Neural Networks
• Simulating first-order phase transition with hierarchical autoregressive networks
• Flow-Based Sampling for Entanglement Entropy and the Machine Learning of Defects
• Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows
• Non-Perturbative Trivializing Flows for Lattice Gauge Theories
• Efficient Optimization of Variational Autoregressive Networks with Natural Gradient
• AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning
• Scaling flow-based approaches for topology sampling in $\mathrm{SU}(3)$ gauge theory
• Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows
• A universal neural network for learning phases and criticalities
• Deep generative modelling of canonical ensemble with differentiable thermal properties
• Study of topological quantities of lattice QCD with a modified Wasserstein generative adversarial network
• Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
• Casimir effect in critical $\mathrm{O}(N)$ models from non-equilibrium Monte Carlo simulations
• Global sampling of Feynman's diagrams through Normalizing Flow
• NeuMC -- a package for neural sampling for lattice field theories
• Hierarchical autoregressive neural networks in three-dimensional statistical system