LeapfrogLayers: A Trainable Framework for Effective Topological Sampling

• URL: http://arxiv.org/abs/2112.01582v1
• Date: Thu, 2 Dec 2021 19:48:16 GMT
• Title: LeapfrogLayers: A Trainable Framework for Effective Topological Sampling
• Authors: Sam Foreman, Xiao-Yong Jin, James C. Osborn
• Abstract summary: We introduce Leapfrogs, an invertible neural network architecture that can be trained to efficiently sample the topology of a 2D $U(1)$ lattice gauge theory. We show an improvement in the integrated autocorrelation time of the topological charge when compared with traditional HMC, and propose methods for scaling our model to larger lattice volumes.
• Score: 0.7366405857677227
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce LeapfrogLayers, an invertible neural network architecture that can be trained to efficiently sample the topology of a 2D $U(1)$ lattice gauge theory. We show an improvement in the integrated autocorrelation time of the topological charge when compared with traditional HMC, and propose methods for scaling our model to larger lattice volumes. Our implementation is open source, and is publicly available on github at https://github.com/saforem2/l2hmc-qcd

Related papers

• Iterative Filter Pruning for Concatenation-based CNN Architectures [9.651318927588934]
  Modern object detectors have highly interconnected convolutional layers with concatenations. We propose a method to handle concatenation layers, based on the connectivity graph of convolutional layers. We deploy pruned models to FPGA and NVIDIA Jetson Xavier AGX.
  arXiv  Detail & Related papers  (2024-05-04T19:40:42Z)
• Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures [85.76673783330334]
  Two different settings of linear weight-sharing layers motivate two flavours of Kronecker-Factored Approximate Curvature (K-FAC) We show they are exact for deep linear networks with weight-sharing in their respective setting. We observe little difference between these two K-FAC variations when using them to train both a graph neural network and a vision transformer.
  arXiv  Detail & Related papers  (2023-11-01T16:37:00Z)
• From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited [51.24526202984846]
  Graph-based semi-supervised learning (GSSL) has long been a hot research topic.<n> graph convolutional networks (GCNs) have become the predominant techniques for their promising performance.<n>We propose three simple but powerful graph convolution methods.
  arXiv  Detail & Related papers  (2023-09-24T10:10:21Z)
• 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)
• A differentiable Gaussian Prototype Layer for explainable Segmentation [3.258592531141818]
  We introduce a gradient-based prototype layer for gradient-based prototype learning. We show it can be used as a novel building block for explainable neural networks.
  arXiv  Detail & Related papers  (2023-06-25T22:33:21Z)
• Efficient Graph Field Integrators Meet Point Clouds [59.27295475120132]
  We present two new classes of algorithms for efficient field integration on graphs encoding point clouds. The first class, SeparatorFactorization(SF), leverages the bounded genus of point cloud mesh graphs, while the second class, RFDiffusion(RFD), uses popular epsilon-nearest-neighbor graph representations for point clouds.
  arXiv  Detail & Related papers  (2023-02-02T08:33:36Z)
• Improved Convergence Guarantees for Shallow Neural Networks [91.3755431537592]
  We prove convergence of depth 2 neural networks, trained via gradient descent, to a global minimum. Our model has the following features: regression with quadratic loss function, fully connected feedforward architecture, RelU activations, Gaussian data instances, adversarial labels. They strongly suggest that, at least in our model, the convergence phenomenon extends well beyond the NTK regime''
  arXiv  Detail & Related papers  (2022-12-05T14:47:52Z)
• AnomalyHop: An SSL-based Image Anomaly Localization Method [47.56319291471639]
  AnomalyHop is an image anomaly localization method based on the successive subspace learning (SSL) framework. AnomalyHop is mathematically transparent, easy to train, and fast in its inference speed. Its area under the ROC curve (ROC-AUC) performance on the MVTec AD dataset is 95.9%, which is among the best of several benchmarking methods.
  arXiv  Detail & Related papers  (2021-05-08T23:17:27Z)
• 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)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case [93.37576644429578]
  Graph neural networks (GNNs) have made great progress recently on learning from graph-structured data in practice. We provide a theoretically-grounded generalizability analysis of GNNs with one hidden layer for both regression and binary classification problems.
  arXiv  Detail & Related papers  (2020-06-25T00:45:52Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

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.