English

Learning Proposals for Practical Energy-Based Regression

Machine Learning 2023-11-08 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

Energy-based models (EBMs) have experienced a resurgence within machine learning in recent years, including as a promising alternative for probabilistic regression. However, energy-based regression requires a proposal distribution to be manually designed for training, and an initial estimate has to be provided at test-time. We address both of these issues by introducing a conceptually simple method to automatically learn an effective proposal distribution, which is parameterized by a separate network head. To this end, we derive a surprising result, leading to a unified training objective that jointly minimizes the KL divergence from the proposal to the EBM, and the negative log-likelihood of the EBM. At test-time, we can then employ importance sampling with the trained proposal to efficiently evaluate the learned EBM and produce stand-alone predictions. Furthermore, we utilize our derived training objective to learn mixture density networks (MDNs) with a jointly trained energy-based teacher, consistently outperforming conventional MDN training on four real-world regression tasks within computer vision. Code is available at https://github.com/fregu856/ebms_proposals.

Keywords

Cite

@article{arxiv.2110.11948,
  title  = {Learning Proposals for Practical Energy-Based Regression},
  author = {Fredrik K. Gustafsson and Martin Danelljan and Thomas B. Schön},
  journal= {arXiv preprint arXiv:2110.11948},
  year   = {2023}
}

Comments

AISTATS 2022. Code is available at https://github.com/fregu856/ebms_proposals

R2 v1 2026-06-24T07:06:50.447Z