Particle Dynamics for Learning EBMs

by   Kirill Neklyudov, et al.

Energy-based modeling is a promising approach to unsupervised learning, which yields many downstream applications from a single model. The main difficulty in learning energy-based models with the "contrastive approaches" is the generation of samples from the current energy function at each iteration. Many advances have been made to accomplish this subroutine cheaply. Nevertheless, all such sampling paradigms run MCMC targeting the current model, which requires infinitely long chains to generate samples from the true energy distribution and is problematic in practice. This paper proposes an alternative approach to getting these samples and avoiding crude MCMC sampling from the current model. We accomplish this by viewing the evolution of the modeling distribution as (i) the evolution of the energy function, and (ii) the evolution of the samples from this distribution along some vector field. We subsequently derive this time-dependent vector field such that the particles following this field are approximately distributed as the current density model. Thereby we match the evolution of the particles with the evolution of the energy function prescribed by the learning procedure. Importantly, unlike Monte Carlo sampling, our method targets to match the current distribution in a finite time. Finally, we demonstrate its effectiveness empirically compared to MCMC-based learning methods.


Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler

Due to the intractable partition function, training energy-based models ...

On the Anatomy of MCMC-based Maximum Likelihood Learning of Energy-Based Models

This study investigates the effects Markov Chain Monte Carlo (MCMC) samp...

Deep Directed Generative Models with Energy-Based Probability Estimation

Training energy-based probabilistic models is confronted with apparently...

Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling

Sampling from an unnormalized probability distribution is a fundamental ...

On Learning Non-Convergent Short-Run MCMC Toward Energy-Based Model

This paper studies a curious phenomenon in learning energy-based model (...

Free energy computation of particles with membrane-mediated interactions via Langevin dynamics

We apply well-established concepts of Langevin sampling to derive a new ...

No MCMC for me: Amortized sampling for fast and stable training of energy-based models

Energy-Based Models (EBMs) present a flexible and appealing way to repre...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset