On Energy-Based Models with Overparametrized Shallow Neural Networks
This work addresses generative modeling for researchers, offering incremental insights by extending known advantages from supervised learning to energy-based models.
The paper investigates energy-based models using overparametrized shallow neural networks, showing that training in the 'active' regime improves adaptivity to low-dimensional data structure compared to the 'lazy' regime, with validation through numerical experiments on synthetic data.
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 "active" regime provide a statistical advantage over their associated "lazy" 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 maximum likelihood and Stein Discrepancy estimators, and we validate our theoretical results with numerical experiments on synthetic data.