mlsanityData to 14 Oct 2026

The Differentiable Cross-Entropy Method

arXiv 1909.12830 ↗First posted 27 Sep 2019cs.LG cs.RO math.OCcited by 27

Not on the map. Why?

Abstract (arXiv)

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. DCEM enables us to fine-tune CEM-based controllers with policy optimization.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 9; 2023: 3; 2024: 2; 2025: 3; 2026: 3.

27 papers.

Sort:

By area:

  1. 2022Tutorial on amortized optimizationcited by 83
  2. 2021CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraintscited by 49
  3. 2021MBRL-Lib: A Modular Library for Model-based Reinforcement Learningcited by 42
  4. 2021Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiationcited by 35
  5. 2021Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registrationcited by 24
  6. 2022SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problemscited by 21
  7. 2021Scalable Online Planning via Reinforcement Learning Fine-Tuningcited by 18
  8. 2021Neuro-algorithmic Policies enable Fast Combinatorial Generalizationcited by 11
  9. 2022Learning to Optimize in Model Predictive Controlcited by 11
  10. 2022Learning Sampling Distributions for Model Predictive Controlcited by 10
  11. 2023A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learningcited by 9
  12. 2023Graph Reinforcement Learning for Network Control via Bi-Level Optimizationcited by 8
15 more
  1. 2021Planning with Learned Dynamic Model for Unsupervised Point Cloud Registrationcited by 7
  2. 2023Deep Model Predictive Optimizationcited by 7
  3. 2022Integrating Symmetry into Differentiable Planning with Steerable Convolutionscited by 6
  4. 2022Scaling up and Stabilizing Differentiable Planning with Implicit Differentiationcited by 6
  5. 2022A Simple Decentralized Cross-Entropy Methodcited by 5
  6. 2022Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMMcited by 3
  7. 2024Preference-Optimized Pareto Set Learning for Blackbox Optimizationcited by 2
  8. 2026SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradientscited by 2
  9. 2022Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Controlcited by 1
  10. 2025Bi-Level Reinforcement Learning Pathway for Sim-to-Real Optimalitycited by 1
  11. 2024Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approachcited by 0
  12. 2025Skill-based Safe Reinforcement Learning with Risk Planningcited by 0
  13. 2025CORL: Reinforcement Learning of MILP Policies Solved via Branch and Boundcited by 0
  14. 2026Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimensioncited by 0
  15. 2026Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFTcited by 0