SciPost Physics

SciPost Phys. 11, 043 (2021) · published 30 August 2021

• doi: 10.21468/SciPostPhys.11.2.043
• pdf
• BiBTeX
• RIS
• Submissions/Reports
• 

Abstract

In this work, we study generative adversarial networks (GANs) as a tool to learn the distribution of spin configurations and to generate samples, conditioned on external tuning parameters or other quantities associated with individual configurations. For concreteness, we focus on two examples of conditional variables---the temperature of the system and the energy of the samples. We show that temperature-conditioned models can not only be used to generate samples across thermal phase transitions, but also be employed as unsupervised indicators of transitions. To this end, we introduce a GAN-fidelity measure that captures the model’s susceptibility to external changes of parameters. The proposed energy-conditioned models are integrated with Monte Carlo simulations to perform over-relaxation steps, which break the Markov chain and reduce auto-correlations. We propose ways of efficiently representing the physical states in our network architectures, e.g., by exploiting symmetries, and to minimize the correlations between generated samples. A detailed evaluation, using the two-dimensional XY model as an example, shows that these incorporations bring in considerable improvements over standard machine-learning approaches. We further study the performance of our architectures when no training data is provided near the critical region.

• Teng et al., Clustering neural quantum states via diffusion maps
  Phys. Rev. B 108, 205152 (2023) [Crossref]
• Damewood et al., Sampling lattices in semi-grand canonical ensemble with autoregressive machine learning
  npj Comput Mater 8, 61 (2022) [Crossref]
• Guo et al., Learning phase transitions from regression uncertainty: a new regression-based machine learning approach for automated detection of phases of matter
  New J. Phys. 25, 083037 (2023) [Crossref]
• Singha et al., Sampling U(1) gauge theory using a retrainable conditional flow-based model
  Phys. Rev. D 108, 074518 (2023) [Crossref]
• Contessi et al., Detection of Berezinskii-Kosterlitz-Thouless transition via Generative Adversarial Networks
  SciPost Phys. 12, 107 (2022) [Crossref]
• Singha et al., Generative learning for the problem of critical slowing down in lattice Gross-Neveu model
  SciPost Phys. Core 5, 052 (2022) [Crossref]
• Del Debbio et al., Efficient modeling of trivializing maps for lattice ϕ4 theory using normalizing flows: A first look at scalability
  Phys. Rev. D 104, 094507 (2021) [Crossref]
• Lu et al., Network-Initialized Monte Carlo Based on Generative Neural Networks
  Chinese Phys. Lett. 39, 050701 (2022) [Crossref]
• Miyajima et al., Machine-learning detection of the Berezinskii-Kosterlitz-Thouless transition and the second-order phase transition in XXZ models
  Phys. Rev. B 107, 134420 (2023) [Crossref]
• Singha et al., Conditional normalizing flow for Markov chain Monte Carlo sampling in the critical region of lattice field theory
  Phys. Rev. D 107, 014512 (2023) [Crossref]
• Zhou et al., Exploring QCD matter in extreme conditions with Machine Learning
  Progress in Particle and Nuclear Physics 135, 104084 104084 (2024) [Crossref]