Jascha Sohl-Dickstein: 'Generalizing Hamiltonian Monte Carlo with Neural Networks'

preview_player
Показать описание
Machine Learning for Physics and the Physics of Learning 2019
Workshop I: From Passive to Active: Generative and Reinforcement Learning with Physics

"Generalizing Hamiltonian Monte Carlo with Neural Networks"
Jascha Sohl-Dickstein, Google

Institute for Pure and Applied Mathematics, UCLA
September 26, 2019

  1. Institute for Pure & Applied Mathematics (IPAM)
  2. ucla
  3. ipam
  4. math
  5. mathematics
  6. machine learning
Рекомендации по теме
Jascha Sohl-Dickstein: 'Generalizing 0:46:55

Jascha Sohl-Dickstein: 'Generalizing Hamiltonian Monte Carlo with Neural Networks'

A General Metric 0:26:38

A General Metric for Riemannian Hamiltonian Monte Carlo (1) Michael Betancourt

CSL seminar: Jascha 0:51:37

CSL seminar: Jascha Sohl-Dickstein - Learned optimizers

Hamiltonian Monte-Carlo for 1:09:43

Hamiltonian Monte-Carlo for Orthogonal Matrices

PhD thesis defense 0:46:26

PhD thesis defense | Hamiltonian Monte Carlo variants | National University of Singapore

A General Metric 0:02:46

A General Metric for Riemannian Hamiltonian Monte Carlo (Q) Michael Betancourt

Supervised Learning of 0:30:03

Supervised Learning of Rules for Unsupervised Representation Learning - Jascha Sohl-Dickstein

Learned Optimizers - 1:25:05

Learned Optimizers - Jascha Sohl-Dickstein

Bayesian tomography using 0:02:22

Bayesian tomography using Hamiltonian Monte Carlo

Michael Betancourt: Scalable 0:53:20

Michael Betancourt: Scalable Bayesian Inference with Hamiltonian Monte Carlo

Bilge:Hamiltonian Monte Carlo 0:12:01

Bilge:Hamiltonian Monte Carlo on the space of phylogenies

10-708: Comparison of 0:10:15

10-708: Comparison of Symplectic Integrators for Hamiltonian Monte Carlo

David Layden (IBM) 0:50:38

David Layden (IBM) | Quanta Seminar

RSS 2021, Spotlight 0:05:04

RSS 2021, Spotlight Talk 67: Hamiltonian-based Neural ODE Networks on the SE(3) Manifold...

Quantum algorithms for 0:43:56

Quantum algorithms for Hamiltonian simulation: Recent results and open problems

Meta-learning of Optimizers 0:47:18

Meta-learning of Optimizers and Update Rules

Quantum Dynamics of 0:10:38

Quantum Dynamics of Machine Learning - ArXiv:2407.19890

Inference in Deep 0:02:51

Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo

Quantum Dynamics of 0:15:28

Quantum Dynamics of Machine Learning - ArXiv:2407.19890

Peadar Coyle - 0:28:59

Peadar Coyle - A modern introduction to Hamiltonian Monte Carlo and Bayesian workflows

Bayesian tomographic reconstruction 0:05:05

Bayesian tomographic reconstruction using Riemannian MCMC

Hamiltonian Nullspace Shuttles 0:04:04

Hamiltonian Nullspace Shuttles

BSU Seminar: 'Sparse 1:03:29

BSU Seminar: 'Sparse Hamiltonian Flows (or: Bayesian Coresets Without all the Fuss)'

Extending Lagrangian & 0:10:07

Extending Lagrangian & Hamiltonian Neural Networks with Differentiable Contact Models | NeurIPS ...