Flow-based Sampling for Entanglement Entropy and the Machine Learning of Defects

• URL: http://arxiv.org/abs/2410.14466v1
• Date: Fri, 18 Oct 2024 13:51:25 GMT
• Title: Flow-based Sampling for Entanglement Entropy and the Machine Learning of Defects
• Authors: Andrea Bulgarelli, Elia Cellini, Karl Jansen, Stefan Kühn, Alessandro Nada, Shinichi Nakajima, Kim A. Nicoli, Marco Panero,
• Abstract summary: We introduce a novel technique to numerically calculate R'enyi entanglement entropies in lattice quantum field theory using generative models. We describe how flow-based approaches can be combined with the replica trick using a custom neural-network architecture around a lattice defect connecting two replicas.
• Score: 38.18440341418837
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We introduce a novel technique to numerically calculate R\'enyi entanglement entropies in lattice quantum field theory using generative models. We describe how flow-based approaches can be combined with the replica trick using a custom neural-network architecture around a lattice defect connecting two replicas. Numerical tests for the $\phi^4$ scalar field theory in two and three dimensions demonstrate that our technique outperforms state-of-the-art Monte Carlo calculations, and exhibit a promising scaling with the defect size.

Related papers

• Pushing the Limits of Large Language Model Quantization via the Linearity Theorem [71.3332971315821]
  We present a "line theoremarity" establishing a direct relationship between the layer-wise $ell$ reconstruction error and the model perplexity increase due to quantization. This insight enables two novel applications: (1) a simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, dubbed HIGGS, and (2) an optimal solution to the problem of finding non-uniform per-layer quantization levels.
  arXiv  Detail & Related papers  (2024-11-26T15:35:44Z)
• The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models [75.33431791218302]
  Deep Neural Network Network (DNN) models are used for programming purposes. In this paper we examine the use of convex neural recovery models. We show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program. We also show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program.
  arXiv  Detail & Related papers  (2023-12-19T23:04:56Z)
• A Deep Dive into the Connections Between the Renormalization Group and Deep Learning in the Ising Model [0.0]
  Renormalization group (RG) is an essential technique in statistical physics and quantum field theory. We develop extensive renormalization techniques for the 1D and 2D Ising model to provide a baseline for comparison. For the 2D Ising model, we successfully generated Ising model samples using the Wolff algorithm, and performed the group flow using a quasi-deterministic method.
  arXiv  Detail & Related papers  (2023-08-21T22:50:54Z)
• Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference [0.0]
  We provide a rigorous analysis of training by variational inference (VI) of Bayesian neural networks. We prove a law of large numbers for three different training schemes. An important result is that all methods converge to the same mean-field limit.
  arXiv  Detail & Related papers  (2023-07-10T07:50:09Z)
• JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models [0.5872014229110214]
  We propose jointly amortized neural approximation'' (JANA) of intractable likelihood functions and posterior densities. We benchmark the fidelity of JANA on a variety of simulation models against state-of-the-art Bayesian methods.
  arXiv  Detail & Related papers  (2023-02-17T20:17:21Z)
• Variational Laplace Autoencoders [53.08170674326728]
  Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. We present a novel approach that addresses the limited posterior expressiveness of fully-factorized Gaussian assumption. We also present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models.
  arXiv  Detail & Related papers  (2022-11-30T18:59:27Z)
• Git Re-Basin: Merging Models modulo Permutation Symmetries [3.5450828190071655]
  We show how simple algorithms can be used to fit large networks in practice. We demonstrate the first (to our knowledge) demonstration of zero mode connectivity between independently trained models. We also discuss shortcomings in the linear mode connectivity hypothesis.
  arXiv  Detail & Related papers  (2022-09-11T10:44:27Z)
• Large-Scale Learning with Fourier Features and Tensor Decompositions [3.6930948691311007]
  We exploit the tensor product structure of deterministic Fourier features, which enables us to represent the model parameters as a low-rank tensor decomposition. We demonstrate by means of numerical experiments how our low-rank tensor approach obtains the same performance of the corresponding nonparametric model.
  arXiv  Detail & Related papers  (2021-09-03T14:12:53Z)
• Deep Learning Hamiltonian Monte Carlo [0.6554326244334867]
  We generalize the Hamiltonian Monte Carlo algorithm with a stack of neural network layers. We demonstrate that our model is able to successfully mix between modes of different topologies.
  arXiv  Detail & Related papers  (2021-05-07T17:50:18Z)
• Joint Network Topology Inference via Structured Fusion Regularization [70.30364652829164]
  Joint network topology inference represents a canonical problem of learning multiple graph Laplacian matrices from heterogeneous graph signals. We propose a general graph estimator based on a novel structured fusion regularization. We show that the proposed graph estimator enjoys both high computational efficiency and rigorous theoretical guarantee.
  arXiv  Detail & Related papers  (2021-03-05T04:42:32Z)
• Primal-Dual Mesh Convolutional Neural Networks [62.165239866312334]
  We propose a primal-dual framework drawn from the graph-neural-network literature to triangle meshes. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them. We provide theoretical insights of our approach using tools from the mesh-simplification literature.
  arXiv  Detail & Related papers  (2020-10-23T14:49:02Z)

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.