SciPost Physics

SciPost Phys. 11, 025 (2021) · published 9 August 2021

• doi: 10.21468/SciPostPhys.11.2.025
• pdf
• BiBTeX
• RIS
• Submissions/Reports
• 

Abstract

We demonstrate how to map out the phase diagram of a two dimensional quantum many body system with no prior physical knowledge by applying deep \textit{anomaly detection} to ground states from infinite projected entangled pair state simulations. As a benchmark, the phase diagram of the 2D frustrated bilayer Heisenberg model is analyzed, which exhibits a second-order and two first-order quantum phase transitions. We show that in order to get a good qualitative picture of the transition lines, it suffices to use data from the cost-efficient simple update optimization. Results are further improved by post-selecting ground-states based on their energy at the cost of contracting the tensor network once. Moreover, we show that the mantra of ``more training data leads to better results'' is not true for the learning task at hand and that, in principle, one training example suffices for this learning task. This puts the necessity of neural network optimizations for these learning tasks in question and we show that, at least for the model and data at hand, a simple geometric analysis suffices.

• Arnold et al., Replacing Neural Networks by Optimal Analytical Predictors for the Detection of Phase Transitions
  Phys. Rev. X 12, 031044 (2022) [Crossref]
• Contessi et al., Detection of Berezinskii-Kosterlitz-Thouless transition via Generative Adversarial Networks
  SciPost Phys. 12, 107 (2022) [Crossref]
• Caro et al., Generalization in quantum machine learning from few training data
  Nat Commun 13, 4919 (2022) [Crossref]
• Huang et al., Provably efficient machine learning for quantum many-body problems
  Science 377, eabk3333 (2022) [Crossref]
• Ng et al., Unsupervised learning of phase transitions via modified anomaly detection with autoencoders
  Phys. Rev. B 108, 214428 (2023) [Crossref]
• Lewis et al., Improved machine learning algorithm for predicting ground state properties
  Nat Commun 15, 895 (2024) [Crossref]
• Szołdra et al., Detecting ergodic bubbles at the crossover to many-body localization using neural networks
  Phys. Rev. B 104, L140202 (2021) [Crossref]
• Kottmann et al., Variational quantum anomaly detection: Unsupervised mapping of phase diagrams on a physical quantum computer
  Phys. Rev. Research 3, 043184 (2021) [Crossref]