A learning algorithm with emergent scaling behavior for classifying phase transitions

• URL: http://arxiv.org/abs/2103.15855v1
• Date: Mon, 29 Mar 2021 18:05:27 GMT
• Title: A learning algorithm with emergent scaling behavior for classifying phase transitions
• Authors: Nishad Maskara, Michael Buchhold, Manuel Endres, Evert van Nieuwenburg
• Abstract summary: We introduce a supervised learning algorithm for studying critical phenomena from measurement data. We test it on the transverse field Ising chain and q=6 Potts model. Our algorithm correctly identifies the thermodynamic phase of the system and extracts scaling behavior from projective measurements.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Machine learning-inspired techniques have emerged as a new paradigm for analysis of phase transitions in quantum matter. In this work, we introduce a supervised learning algorithm for studying critical phenomena from measurement data, which is based on iteratively training convolutional networks of increasing complexity, and test it on the transverse field Ising chain and q=6 Potts model. At the continuous Ising transition, we identify scaling behavior in the classification accuracy, from which we infer a characteristic classification length scale. It displays a power-law divergence at the critical point, with a scaling exponent that matches with the diverging correlation length. Our algorithm correctly identifies the thermodynamic phase of the system and extracts scaling behavior from projective measurements, independently of the basis in which the measurements are performed. Furthermore, we show the classification length scale is absent for the $q=6$ Potts model, which has a first order transition and thus lacks a divergent correlation length. The main intuition underlying our finding is that, for measurement patches of sizes smaller than the correlation length, the system appears to be at the critical point, and therefore the algorithm cannot identify the phase from which the data was drawn.

Related papers

• Particle density and critical point for studying site percolation by finite size scaling [6.449416869164504]
  We study the relationship between particle number density, critical point, and latent variables in the site percolation model. Unsupervised learning yields reliable results consistent with Monte Carlo simulations.
  arXiv  Detail & Related papers  (2023-11-20T10:21:50Z)
• In-Context Convergence of Transformers [63.04956160537308]
  We study the learning dynamics of a one-layer transformer with softmax attention trained via gradient descent. For data with imbalanced features, we show that the learning dynamics take a stage-wise convergence process.
  arXiv  Detail & Related papers  (2023-10-08T17:55:33Z)
• Gradient-Based Feature Learning under Structured Data [57.76552698981579]
  In the anisotropic setting, the commonly used spherical gradient dynamics may fail to recover the true direction. We show that appropriate weight normalization that is reminiscent of batch normalization can alleviate this issue. In particular, under the spiked model with a suitably large spike, the sample complexity of gradient-based training can be made independent of the information exponent.
  arXiv  Detail & Related papers  (2023-09-07T16:55:50Z)
• Fluctuation based interpretable analysis scheme for quantum many-body snapshots [0.0]
  Microscopically understanding and classifying phases of matter is at the heart of strongly-correlated quantum physics. Here, we combine confusion learning with correlation convolutional neural networks, which yields fully interpretable phase detection. Our work opens new directions in interpretable quantum image processing being sensible to long-range order.
  arXiv  Detail & Related papers  (2023-04-12T17:59:59Z)
• Evolution of many-body systems under ancilla quantum measurements [58.720142291102135]
  We study the concept of implementing quantum measurements by coupling a many-body lattice system to an ancillary degree of freedom. We find evidence of a disentangling-entangling measurement-induced transition as was previously observed in more abstract models.
  arXiv  Detail & Related papers  (2023-03-13T13:06:40Z)
• Learning Optical Flow from a Few Matches [67.83633948984954]
  We show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it. Experiments show that our method can reduce computational cost and memory use significantly, while maintaining high accuracy.
  arXiv  Detail & Related papers  (2021-04-05T21:44:00Z)
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition [0.7658140759553149]
  We investigate the connection between the supervised learning of the binary phase classification in the ferromagnetic Ising model and the standard finite-size-scaling theory of the second-order phase transition. We show that just one free parameter is capable enough to describe the data-driven emergence of the universal finite-size-scaling function in the network output.
  arXiv  Detail & Related papers  (2020-10-01T12:34:12Z)
• Interpolation and Learning with Scale Dependent Kernels [91.41836461193488]
  We study the learning properties of nonparametric ridge-less least squares. We consider the common case of estimators defined by scale dependent kernels.
  arXiv  Detail & Related papers  (2020-06-17T16:43:37Z)
• Unsupervised phase discovery with deep anomaly detection [0.0]
  We demonstrate how to explore phase diagrams with automated and unsupervised machine learning. We employ deep neural networks to determine the entire phase diagram in a completely unsupervised and automated fashion. Our method allows us to reveal a phase-separated region between supersolid and superfluid parts with unexpected properties.
  arXiv  Detail & Related papers  (2020-03-22T14:20:04Z)
• Mean-field entanglement transitions in random tree tensor networks [0.0]
  Entanglement phase transitions in quantum chaotic systems have emerged as a new class of critical points separating phases with different entanglement scaling. We propose a mean-field theory of such transitions by studying the entanglement properties of random tree tensor networks.
  arXiv  Detail & Related papers  (2020-03-02T19:00:19Z)
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees [106.91654068632882]
  We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution. We show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.
  arXiv  Detail & Related papers  (2020-03-02T16:40:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.