mlsanityData to 7 Oct 2026

Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders

arXiv 1703.02435 ↗First posted 7 Mar 2017cond-mat.stat-mech cs.LG stat.MLcited by 47

Not on the map. Why?

Abstract (arXiv)

We employ unsupervised machine learning techniques to learn latent parameters which best describe states of the two-dimensional Ising model and the three-dimensional XY model. These methods range from principal component analysis to artificial neural network based variational autoencoders. The states are sampled using a Monte-Carlo simulation above and below the critical temperature. We find that the predicted latent parameters correspond to the known order parameters. The latent representation of the states of the models in question are clustered, which makes it possible to identify phases without prior knowledge of their existence or the underlying Hamiltonian. Furthermore, we find that the reconstruction loss function can be used as a universal identifier for phase transitions.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 4; 2024: 7; 2025: 11; 2026: 10.

47 papers.

Sort:

By area:

  1. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 116
  2. 2021Universal Adversarial Examples and Perturbations for Quantum Classifierscited by 22
  3. 2021Machine learning discovery of new phases in programmable quantum simulator snapshotscited by 13
  4. 2025Interpretable Machine Learning in Physics: A Reviewcited by 11
  5. 2023Explainable Representation Learning of Small Quantum Statescited by 10
  6. 2022Learning Summary Statistics for Bayesian Inference with Autoencoderscited by 9
  7. 2025Artificial intelligence for representing and characterizing quantum systemscited by 9
  8. 2023Exponentially improved efficient machine learning for quantum many-body states with provable guaranteescited by 7
  9. 2023Learning minimal representations of stochastic processes with variational autoencoderscited by 7
  10. 2024Phase Transitions in the Output Distribution of Large Language Modelscited by 7
  11. 2024AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learningcited by 6
  12. 2025Interpretable representation learning of quantum data enabled by probabilistic variational autoencoderscited by 6
35 more
  1. 2021Neural network based order parameter for phase transitions and its applications in high-entropy alloyscited by 4
  2. 2025Unsupervised learning for anticipating critical transitionscited by 4
  3. 2022A simple framework for contrastive learning phases of mattercited by 3
  4. 2025Unraveling Quantum Environments: Transformer-Assisted Learning in Lindblad Dynamicscited by 3
  5. 2026Discovering quantum phenomena with Interpretable Machine Learningcited by 3
  6. 2022Learning entanglement breakdown as a phase transition by confusioncited by 2
  7. 2022A Group-Equivariant Autoencoder for Identifying Spontaneously Broken Symmetriescited by 2
  8. 2022Rotated Digit Recognition by Variational Autoencoders with Fixed Output Distributionscited by 2
  9. 2024A review of unsupervised learning in astronomycited by 2
  10. 2024Advancing Spatio-temporal Storm Surge Prediction with Hierarchical Deep Neural Networkscited by 2
  11. 2026Disentanglement by means of action-induced representationscited by 2
  12. 2021Can a CNN trained on the Ising model detect the phase transition of the q-state Potts model?cited by 1
  13. 2021Weighted Quantum Channel Compiling through Proximal Policy Optimizationcited by 1
  14. 2021Feature extraction of machine learning and phase transition point of Ising modelcited by 1
  15. 2022Inferring topological transitions in pattern-forming processes with self-supervised learningcited by 1
  16. 2023Machine learning for structure-property relationships: Scalability and limitationscited by 1
  17. 2024Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradientscited by 1
  18. 2021Direct detection of plasticity onset through total-strain profile evolutioncited by 0
  19. 2021Anomaly Detection of Wind Turbine Time Series using Variational Recurrent Autoencoderscited by 0
  20. 2022Snake net and balloon force with a neural network for detecting multiple phasescited by 0
  21. 2024Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representationscited by 0
  22. 2025Uncovering Magnetic Phases with Synthetic Data and Physics-Informed Trainingcited by 0
  23. 2025Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Modelscited by 0
  24. 2025A Generative Model for Disentangling Galaxy Photometric Parameterscited by 0
  25. 2025Quantum Circuits for Quantum Convolutions: A Quantum Convolutional Autoencodercited by 0
  26. 2025Attention to Order: Transformers Discover Phase Transitions via Learnabilitycited by 0
  27. 2025On the flow matching interpretabilitycited by 0
  28. 2026Capturing the Topological Phase Transition and Thermodynamics of the 2D XY Model via Manifold-Aware Score-Based Generative Modelingcited by 0
  29. 2026From Classical to Quantum: Extending Prometheus for Unsupervised Discovery of Phase Transitions in Three Dimensions and Quantum Systemscited by 0
  30. 2026Unsupervised Discovery of Intermediate Phase Order in the Frustrated J1-J2 Heisenberg Model via Prometheus Frameworkcited by 0
  31. 2026AI-Driven Phase Identification from X-ray Hyperspectral Imaging of cycled Na-ion Cathode Materialscited by 0
  32. 2026Beam-Plasma Collective Oscillations in Intense Charged-Particle Beams: Dielectric Response Theory, Langmuir Wave Dispersion, and Unsupervised Detection via Prometheuscited by 0
  33. 2026Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE methodcited by 0
  34. 2026TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator datacited by 0
  35. 2026Autonomous phase discoverycited by 0