Can Boltzmann Machines Discover Cluster Updates ?

Abstract

Boltzmann machines are physics informed generative models with wide applications in machine learning. They can learn the probability distribution from an input dataset and generate new samples accordingly. Applying them back to physics, the Boltzmann machines are ideal recommender systems to accelerate Monte Carlo simulation of physical systems due to their flexibility and effectiveness. More intriguingly, we show that the generative sampling of the Boltzmann Machines can even discover unknown cluster Monte Carlo algorithms. The creative power comes from the latent representation of the Boltzmann machines, which learn to mediate complex interactions and identify clusters of the physical system. We demonstrate these findings with concrete examples of the classical Ising model with and without four spin plaquette interactions. Our results endorse a fresh research paradigm where intelligent machines are designed to create or inspire human discovery of innovative algorithms.

arXiv comment4 pages, 4 figures, and half page appendix

References in corpus (24)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Learning phase transitions by confusion
• The ALPS project release 2.0: Open source software for strongly correlated systems
• Two-step melting in two dimensions: First-order liquid-hexatic transition
• Discovering Phase Transitions with Unsupervised Learning
• Quantum Entanglement in Neural Network States
• Cluster Algorithm for Vertex Models
• Worm algorithms for classical statistical models
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• The Loop Algorithm
• Learning Thermodynamics with Boltzmann Machines
• Self-Learning Monte Carlo Method
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• A Neural Decoder for Topological Codes
• Universal Amplitude Ratios in the Critical Two-Dimensional Ising Model on a Torus
• Recent Developments of World-Line Monte Carlo Methods
• The fermion bag approach to lattice field theories
• Self-Learning Monte Carlo Method in Fermion Systems
• Self-Learning Determinantal Quantum Monte Carlo Method
• Estimating errors reliably in Monte Carlo simulations of the Ehrenfest model
• Dual Monte Carlo and Cluster Algorithms
• Generalization of the Fortuin-Kasteleyn transformation and its application to quantum spin simulations,
• Recommender Engine for Continuous Time Quantum Monte Carlo Methods

Cited by in corpus (28)

• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Approximating quantum many-body wave-functions using artificial neural networks
• Equivariant flow-based sampling for lattice gauge theory
• Constructing neural stationary states for open quantum many-body systems
• Machine Learning for Quantum Matter
• Machine learning of phase transitions in the percolation and XY models
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Revisiting the Hybrid Quantum Monte Carlo Method for Hubbard and Electron-Phonon Models
• Learning Disordered Topological Phases by Statistical Recovery of Symmetry
• Machine learning action parameters in lattice quantum chromodynamics
• Smallest Neural Network to Learn the Ising Criticality
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Gauge-equivariant flow models for sampling in lattice field theories with pseudofermions
• Status and Future Perspectives for Lattice Gauge Theory Calculations to the Exascale and Beyond
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
• Extending machine learning classification capabilities with histogram reweighting
• Generalizing Hamiltonian Monte Carlo with Neural Networks
• Policy Guided Monte Carlo: Reinforcement Learning Markov Chain Dynamics
• Transforming Generalized Ising Model into Boltzmann Machine
• Cluster Percolation in the Two-Dimensional Ising Spin Glass
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• Phase classification in the long-range Harper model using machine learning
• Cluster percolation in the three-dimensional $\pm J$ random-bond Ising model
• Discovering quasiorder parameters in the Potts model: A bridge between machine learning and critical phenomena