On Feature Diversity in Energy-based Models
This work addresses performance bottlenecks in EBMs for machine learning practitioners, though it is incremental as it builds on existing PAC theory.
The paper tackles the problem of feature redundancy in energy-based models (EBMs) by extending PAC theory to analyze its effect on performance, showing that reducing redundancy consistently decreases the gap between true and empirical energy expectations and boosts model performance across regression, classification, and implicit regression contexts.
Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-model(s) that learn a combination of the different features to generate an energy mapping for each input configuration. In this paper, we focus on the diversity of the produced feature set. We extend the probably approximately correct (PAC) theory of EBMs and analyze the effect of redundancy reduction on the performance of EBMs. We derive generalization bounds for various learning contexts, i.e., regression, classification, and implicit regression, with different energy functions and we show that indeed reducing redundancy of the feature set can consistently decrease the gap between the true and empirical expectation of the energy and boosts the performance of the model.