ICML 2020poster69 citations

The Differentiable Cross-Entropy Method

Brandon Amos, Denis Yarats

Abstract

We study the Cross-Entropy Method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function’s parameters. In the machine learning setting this brings CEM inside of the end-to-end learning pipeline where this has otherwise been impossible. We show applications in a synthetic energy-based structured prediction task and in non-convex continuous control. In the control setting we show how to embed optimal action sequences into a lower-dimensional space. This enables us to use policy optimization to fine-tune modeling components by differentiating through the CEM-based controller.

BibTeX
@InProceedings{pmlr-v119-amos20a,
  title = 	 {The Differentiable Cross-Entropy Method},
  author =       {Amos, Brandon and Yarats, Denis},
  booktitle = 	 {Proceedings of the 37th International Conference on Machine Learning},
  pages = 	 {291--302},
  year = 	 {2020},
  editor = 	 {III, Hal Daumé and Singh, Aarti},
  volume = 	 {119},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--18 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v119/amos20a/amos20a.pdf},
  url = 	 {https://proceedings.mlr.press/v119/amos20a.html},
  abstract = 	 {We study the Cross-Entropy Method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function’s parameters. In the machine learning setting this brings CEM inside of the end-to-end learning pipeline where this has otherwise been impossible. We show applications in a synthetic energy-based structured prediction task and in non-convex continuous control. In the control setting we show how to embed optimal action sequences into a lower-dimensional space. This enables us to use policy optimization to fine-tune modeling components by differentiating through the CEM-based controller.}
}
The Differentiable Cross-Entropy Method · ICML 2020