On Energy-Based Models with Overparametrized Shallow Neural Networks
Carles Domingo-Enrich,u00a0Alberto Bietti,u00a0Eric Vanden-Eijnden,u00a0Joan Bruna
Energy-based models (EBMs) are a simple yet powerful framework for generative modeling. They are based on a trainable energy function which defines an associated Gibbs measure, and they can be trained and sampled from via well-established statistical tools, such as MCMC. Neural networks may be used as energy function approximators, providing both a rich class of expressive models as well as a flexible device to incorporate data structure. In this work we focus on shallow neural networks. Building from the incipient theory of overparametrized neural networks, we show that models trained in the so-called u2019activeu2019 regime provide a statistical advantage over their associated u2019lazyu2019 or kernel regime, leading to improved adaptivity to hidden low-dimensional structure in the data distribution, as already observed in supervised learning. Our study covers both the maximum likelihood and Stein Discrepancy estimators, and we validate our theoretical results with numerical experiments on synthetic data.
