DeepAI AI Chat
Log In Sign Up

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

by   Will Grathwohl, et al.

Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty. Despite recent advances, training EBMs on high-dimensional data remains a challenging problem as the state-of-the-art approaches are costly, unstable, and require considerable tuning and domain expertise to apply successfully. In this work, we present a simple method for training EBMs at scale which uses an entropy-regularized generator to amortize the MCMC sampling typically used in EBM training. We improve upon prior MCMC-based entropy regularization methods with a fast variational approximation. We demonstrate the effectiveness of our approach by using it to train tractable likelihood models. Next, we apply our estimator to the recently proposed Joint Energy Model (JEM), where we match the original performance with faster and stable training. This allows us to extend JEM models to semi-supervised classification on tabular data from a variety of continuous domains.


page 22

page 23

page 24

page 25

page 26

page 27

page 28

page 29


Implicit Generation and Generalization in Energy-Based Models

Energy based models (EBMs) are appealing due to their generality and sim...

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

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

Balanced Training of Energy-Based Models with Adaptive Flow Sampling

Energy-based models (EBMs) are versatile density estimation models that ...

Energy Discrepancies: A Score-Independent Loss for Energy-Based Models

Energy-based models are a simple yet powerful class of probabilistic mod...

Particle Dynamics for Learning EBMs

Energy-based modeling is a promising approach to unsupervised learning, ...

On Energy-Based Models with Overparametrized Shallow Neural Networks

Energy-based models (EBMs) are a simple yet powerful framework for gener...

Code Repositories