Mutual information of spin systems from autoregressive neural networks

• URL: http://arxiv.org/abs/2304.13412v2
• Date: Thu, 26 Oct 2023 12:47:48 GMT
• Title: Mutual information of spin systems from autoregressive neural networks
• Authors: Piotr Bia{\l}as, Piotr Korcyl, Tomasz Stebel
• Abstract summary: We describe a new direct method to estimate bipartite mutual information of a classical spin system based on Monte Carlo sampling. We demonstrate it on the Ising model for four partitionings, including a multiply-connected even-odd division.
• Score: 0.018416014644193065
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We describe a new direct method to estimate bipartite mutual information of a classical spin system based on Monte Carlo sampling enhanced by autoregressive neural networks. It allows studying arbitrary geometries of subsystems and can be generalized to classical field theories. We demonstrate it on the Ising model for four partitionings, including a multiply-connected even-odd division. We show that the area law is satisfied for temperatures away from the critical temperature: the constant term is universal, whereas the proportionality coefficient is different for the even-odd partitioning.

Related papers

• The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity [0.7499722271664144]
  We study how non-linear activation functions contribute to shaping neural networks' implicit bias. We show that local dynamical attractors facilitate the formation of clusters of hyperplanes where the input to a neuron's activation function is zero.
  arXiv  Detail & Related papers  (2025-03-13T17:36:46Z)
• Learning state and proposal dynamics in state-space models using differentiable particle filters and neural networks [25.103069515802538]
  We introduce a new method, StateMixNN, that uses a pair of neural networks to learn the proposal distribution and transition distribution of a particle filter. Our method is trained targeting the log-likelihood, thereby requiring only the observation series. The proposed method significantly improves recovery of the hidden state in comparison with the state-of-the-art, showing greater improvement in highly non-linear scenarios.
  arXiv  Detail & Related papers  (2024-11-23T19:30:56Z)
• On a Matrix Ensemble for Arbitrary Complex Quantum Systems [0.0]
  We study a variation of the eigenvector ensemble initially proposed by Deutsch for the foundations of the Eigenstate Thermalization Hypothesis (ETH) We focus on the remnants of system-specific information that modify the late-time behavior of correlation functions. We show that for small energy windows correlation functions defined by the new ensemble reduce to the predictions of the ETH.
  arXiv  Detail & Related papers  (2024-07-29T23:17:45Z)
• Rényi entanglement entropy of spin chain with Generative Neural Networks [0.0]
  We describe a method to estimate R'enyi entanglement entropy of a spin system. It is based on the replica trick and generative neural networks with explicit probability estimation. We demonstrate our method on a one-dimensional quantum Ising spin chain.
  arXiv  Detail & Related papers  (2024-06-10T11:44:54Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• Post-Regularization Confidence Bands for Ordinary Differential Equations [6.3582148777824115]
  We construct confidence band for individual regulatory function in ODE with unknown functionals and noisy data observations. We show that the constructed confidence band has the desired kernel coverage probability, and the recovered regulatory network approaches the truth with probability tending to one.
  arXiv  Detail & Related papers  (2021-10-24T19:21:10Z)
• Two-layer neural networks with values in a Banach space [1.90365714903665]
  We study two-layer neural networks whose domain and range are Banach spaces with separable preduals. As the nonlinearity we choose the lattice operation of taking the positive part; in case of $mathbb Rd$-valued neural networks this corresponds to the ReLU activation function.
  arXiv  Detail & Related papers  (2021-05-05T14:54:24Z)
• Deep Archimedean Copulas [98.96141706464425]
  ACNet is a novel differentiable neural network architecture that enforces structural properties. We show that ACNet is able to both approximate common Archimedean Copulas and generate new copulas which may provide better fits to data.
  arXiv  Detail & Related papers  (2020-12-05T22:58:37Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data [52.78581260260455]
  We propose a general method to construct a convolutional layer that is equivariant to transformations from any specified Lie group. We apply the same model architecture to images, ball-and-stick molecular data, and Hamiltonian dynamical systems.
  arXiv  Detail & Related papers  (2020-02-25T17:40:38Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.