No MCMC for me: Amortized sampling for fast and stable training of energy-based models
This addresses the problem of costly and unstable EBM training for researchers and practitioners, offering an incremental improvement over prior methods.
The paper tackles the challenge of training Energy-Based Models (EBMs) on high-dimensional data by introducing a method that uses an entropy-regularized generator to amortize MCMC sampling, resulting in faster and stable training that matches original performance in models like JEM and enables semi-supervised classification on tabular data.
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.