Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling

11/03/2021
by   Greg Ver Steeg, et al.
135

Sampling from an unnormalized probability distribution is a fundamental problem in machine learning with applications including Bayesian modeling, latent factor inference, and energy-based model training. After decades of research, variations of MCMC remain the default approach to sampling despite slow convergence. Auxiliary neural models can learn to speed up MCMC, but the overhead for training the extra model can be prohibitive. We propose a fundamentally different approach to this problem via a new Hamiltonian dynamics with a non-Newtonian momentum. In contrast to MCMC approaches like Hamiltonian Monte Carlo, no stochastic step is required. Instead, the proposed deterministic dynamics in an extended state space exactly sample the target distribution, specified by an energy function, under an assumption of ergodicity. Alternatively, the dynamics can be interpreted as a normalizing flow that samples a specified energy model without training. The proposed Energy Sampling Hamiltonian (ESH) dynamics have a simple form that can be solved with existing ODE solvers, but we derive a specialized solver that exhibits much better performance. ESH dynamics converge faster than their MCMC competitors enabling faster, more stable training of neural network energy models.

READ FULL TEXT

page 8

page 9

page 10

page 20

page 31

research
12/16/2022

Microcanonical Hamiltonian Monte Carlo

We develop Microcanonical Hamiltonian Monte Carlo (MCHMC), a class of mo...
research
07/06/2021

Energy-preserving splitting integrators for sampling from Gaussian distributions with Hamiltonian Monte Carlo method

The diffusive behaviour of simple random-walk proposals of many Markov C...
research
09/29/2020

Couplings for Andersen Dynamics

Andersen dynamics is a standard method for molecular simulations, and a ...
research
06/12/2020

Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC

Learning energy-based model (EBM) requires MCMC sampling of the learned ...
research
11/26/2021

Particle Dynamics for Learning EBMs

Energy-based modeling is a promising approach to unsupervised learning, ...
research
05/16/2022

Ergodic variational flows

This work presents a new class of variational family – ergodic variation...
research
09/13/2023

Harvesting Brownian Motion: Zero Energy Computational Sampling

The key factor currently limiting the advancement of computational power...

Please sign up or login with your details

Forgot password? Click here to reset