Official implementation (PyTorch) of the paper:
Learning Proposals for Practical Energy-Based Regression, AISTATS 2022 [arXiv] [project].
Fredrik K. Gustafsson, Martin Danelljan, Thomas B. Schön.
We derive an efficient and convenient objective that can be employed to train a parameterized distribution q(y|x; phi) by directly minimizing its KL divergence to a conditional EBM p(y|x; theta). We then employ the proposed objective to jointly learn an effective MDN proposal distribution during EBM training, thus addressing the main practical limitations of energy-based regression. Furthermore, we utilize our derived training objective to learn MDNs with a jointly trained energy-based teacher, consistently outperforming conventional MDN training on four real-world regression tasks within computer vision.

If you find this work useful, please consider citing:

@inproceedings{gustafsson2022learning,
  author={Gustafsson, Fredrik K and Danelljan, Martin and Sch{\"o}n, Thomas B},
  title={Learning Proposals for Practical Energy-Based Regression},
  booktitle={Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)},
  year = {2022}
}