Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning

Abstract

Machine learning has the potential to aid our understanding of phase structures in lattice quantum field theories through the statistical analysis of Monte Carlo samples. Available algorithms, in particular those based on deep learning, often demonstrate remarkable performance in the search for previously unidentified features, but tend to lack transparency if applied naively. To address these shortcomings, we propose representation learning in combination with interpretability methods as a framework for the identification of observables. More specifically, we investigate action parameter regression as a pretext task while using layer-wise relevance propagation (LRP) to identify the most important observables depending on the location in the phase diagram. The approach is put to work in the context of a scalar Yukawa model in (2+1)d. First, we investigate a multilayer perceptron to determine an importance hierarchy of several predefined, standard observables. The method is then applied directly to the raw field configurations using a convolutional network, demonstrating the ability to reconstruct all order parameters from the learned filter weights. Based on our results, we argue that due to its broad applicability, attribution methods such as LRP could prove a useful and versatile tool in our search for new physical insights. In the case of the Yukawa model, it facilitates the construction of an observable that characterises the symmetric phase.

arXiv comment13 pages, 11 figures

References in corpus (27)

• Scikit-learn: Machine Learning in Python
• Methods for Interpreting and Understanding Deep Neural Networks
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• A high-bias, low-variance introduction to Machine Learning for physicists
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Machine learning quantum phases of matter beyond the fermion sign problem
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Machine Learning Phases of Strongly Correlated Fermions
• Self-Learning Monte Carlo Method
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Detection of phase transition via convolutional neural network
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Kernel methods for interpretable machine learning of order parameters
• Asymptotically unbiased estimation of physical observables with neural samplers
• Regressive and generative neural networks for scalar field theory
• Parameter diagnostics of phases and phase transition learning by neural networks
• Unsupervised identification of topological order using predictive models
• Machine learning action parameters in lattice quantum chromodynamics
• Learning multiple order parameters with interpretable machines
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Phase transition encoded in neural network

Cited by in corpus (28)

• Machine Learning in Nuclear Physics
• Machine Learning for Quantum Matter
• Phase Transitions in Particle Physics -- Results and Perspectives from Lattice Quantum Chromo-Dynamics
• Exploring QCD matter in extreme conditions with Machine Learning
• Spectral Reconstruction with Deep Neural Networks
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• Lattice gauge equivariant convolutional neural networks
• Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
• Stochastic normalizing flows as non-equilibrium transformations
• Quantitative and Interpretable Order Parameters for Phase Transitions from Persistent Homology
• Quantum field-theoretic machine learning
• Learning Lattice Quantum Field Theories with Equivariant Continuous Flows
• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Machine-learning physics from unphysics: Finding deconfinement temperature in lattice Yang-Mills theories from outside the scaling window
• Interpretable and unsupervised phase classification
• Generalization capabilities of translationally equivariant neural networks
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Disentangling a Deep Learned Volume Formula
• Learning minimal representations of stochastic processes with variational autoencoders
• Confinement in non-Abelian lattice gauge theory via persistent homology
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Building imaginary-time thermal field theory with artificial neural networks
• Preserving gauge invariance in neural networks
• Learning Langevin dynamics with QCD phase transition