The Differentiable Cross-Entropy Method

Brandon Amos · Denis Yarats

Keywords: [ Non-convex Optimization ] [ Planning and Control ] [ Structured Prediction ] [ Meta-learning and Automated ML ] [ Optimization - Non-convex ]


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.

Chat is not available.