LeapfrogLayers: A Trainable Framework for Effective Topological Sampling

v1v2 (latest)

LeapfrogLayers: A Trainable Framework for Effective Topological Sampling

2 December 2021

James C. Osborn

ArXiv (abs)PDF HTML Github (68★)

Papers citing "LeapfrogLayers: A Trainable Framework for Effective Topological Sampling"

9 / 9 papers shown

Title
Introduction to Normalizing Flows for Lattice Field Theory M. S. Albergo D. Boyda D. Hackett G. Kanwar Kyle Cranmer S. Racanière Danilo Jimenez Rezende P. Shanahan AI4CE 79 58 0 20 Jan 2021
Orbital MCMC Kirill Neklyudov Max Welling 64 7 0 15 Oct 2020
A Neural Network MCMC sampler that maximizes Proposal Entropy Zengyi Li Yubei Chen Friedrich T. Sommer 90 15 0 07 Oct 2020
Involutive MCMC: a Unifying Framework Kirill Neklyudov Max Welling Evgenii Egorov Dmitry Vetrov 89 38 0 30 Jun 2020
You say Normalizing Flows I see Bayesian Networks Antoine Wehenkel Gilles Louppe TPM BDL UQCV 48 9 0 01 Jun 2020
Equivariant flow-based sampling for lattice gauge theory G. Kanwar M. S. Albergo D. Boyda Kyle Cranmer D. Hackett S. Racanière Danilo Jimenez Rezende P. Shanahan AI4CE 66 176 0 13 Mar 2020
Neural Network Renormalization Group Shuo-Hui Li Lei Wang BDL DRL 97 125 0 08 Feb 2018
Generalizing Hamiltonian Monte Carlo with Neural Networks Daniel Levy Matthew D. Hoffman Jascha Narain Sohl-Dickstein BDL 79 130 0 25 Nov 2017
Faster Eigenvector Computation via Shift-and-Invert Preconditioning Dan Garber Laurent Dinh Chi Jin Jascha Narain Sohl-Dickstein Samy Bengio Praneeth Netrapalli Aaron Sidford 277 3,723 0 26 May 2016