mlsanityData to 14 Oct 2026

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

arXiv 2607.20674 ↗First posted 22 Jul 2026cs.LG cs.SY eess.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 51 of its 78 references that are in the map. First posted on arXiv 22 Jul 2026.

Builds on

51 of 78 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  5. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 641
  6. 2019Deep Equilibrium Modelscited by 615
  7. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 599
  8. 2019Differentiable Convex Optimization Layerscited by 465
  9. 2018Reward Constrained Policy Optimizationcited by 417
  10. 2019Control Barrier Functions: Theory and Applicationscited by 372
  11. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
  12. 2018Differentiable MPC for End-to-end Planning and Controlcited by 189
38 more
  1. 2020Multiscale Deep Equilibrium Modelscited by 151
  2. 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 151
  3. 2019Implicit Deep Learningcited by 124
  4. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 118
  5. 2020Monotone operator equilibrium networkscited by 100
  6. 2019A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problemscited by 97
  7. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 92
  8. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 88
  9. 2019Differentiating Through a Cone Programcited by 73
  10. 2021Stabilizing Equilibrium Models by Jacobian Regularizationcited by 72
  11. 2019Learning for Safety-Critical Control with Control Barrier Functionscited by 69
  12. 2020Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functionscited by 68
  13. 2019Pontryagin Differentiable Programming: An End-to-End Learning and Control Frameworkcited by 52
  14. 2023How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systemscited by 44
  15. 2020Alternating the Population and Control Neural Networks to Solve High-Dimensional Stochastic Mean-Field Gamescited by 35
  16. 2015A Three-Operator Splitting Scheme and its Optimization Applicationscited by 34
  17. 2019Control Barrier Functions for Systems with High Relative Degreecited by 31
  18. 2021Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimizationcited by 31
  19. 2024HardNet: Hard-Constrained Neural Networks with Universal Approximation Guaranteescited by 31
  20. 2021Run Time Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systemscited by 27
  21. 2021Safe Pontryagin Differentiable Programmingcited by 26
  22. 2021A predictive safety filter for learning-based racing controlcited by 20
  23. 2021Robust Implicit Networks via Non-Euclidean Contractionscited by 20
  24. 2021A Neural Network Approach for High-Dimensional Optimal Control Applied to Multi-Agent Path Findingcited by 18
  25. 2021Feasibility-based Fixed Point Networkscited by 17
  26. 2022Taming Hyperparameter Tuning in Continuous Normalizing Flows Using the JKO Schemecited by 17
  27. 2020A Neural Network Approach Applied to Multi-Agent Optimal Controlcited by 14
  28. 2022Explainable AI via Learning to Optimizecited by 14
  29. 2023Differentiating Through Integer Linear Programs with Quadratic Regularization and Davis-Yin Splittingcited by 11
  30. 2023Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Controlcited by 9
  31. 2025End-to-End Probabilistic Framework for Learning with Hard Constraintscited by 9
  32. 2024Neural Network Approaches for Parameterized Optimal Controlcited by 8
  33. 2025Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiencycited by 8
  34. 2024On Logical Extrapolation for Mazes with Recurrent and Implicit Networkscited by 7
  35. 2022Differentiable Predictive Control with Safety Guarantees: A Control Barrier Function Approachcited by 6
  36. 2025Stability of Transformers under Layer Normalizationcited by 5
  37. 2024Kernel Expansions for High-Dimensional Mean-Field Control with Non-local Interactionscited by 3
  38. 2025End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagationcited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.