mlsanityData to 14 Oct 2026

Safety and optimality in learning-based control at low computational cost

arXiv 2505.08026 ↗First posted 12 May 2025eess.SY cs.LG cs.SYcited by 2

Not on the map. Why?

Abstract (arXiv)

Applying machine learning methods to physical systems that are supposed to act in the real world requires providing safety guarantees. However, methods that include such guarantees often come at a high computational cost, making them inapplicable to large datasets and embedded devices with low computational power. In this paper, we propose CoLSafe, a computationally lightweight safe learning algorithm whose computational complexity grows sublinearly with the number of data points. We derive both safety and optimality guarantees and showcase the effectiveness of our algorithm on a seven-degrees-of-freedom robot arm.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 47 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

18 of 47 references.

References · 18

  1. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  3. 2018When Gaussian Process Meets Big Data: A Review of Scalable GPscited by 206
  4. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  5. 2014Bayesian Optimization with Unknown Constraintscited by 109
  6. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  7. 2015Safe Controller Optimization for Quadrotors with Gaussian Processescited by 78
  8. 2019Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspacescited by 73
  9. 2015A General Framework for Constrained Bayesian Optimization using Information-based Searchcited by 50
  10. 2016Automatic LQR Tuning Based on Gaussian Process Global Optimizationcited by 30
  11. 2021GoSafe: Globally Optimal Safe Robot Learningcited by 27
  12. 2022GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systemscited by 17
6 more
  1. 2020Robot Learning with Crash Constraintscited by 15
  2. 2017Deep Kernels for Optimizing Locomotion Controllerscited by 14
  3. 2021Safe and Efficient Model-free Adaptive Control via Bayesian Optimizationcited by 10
  4. 2022Information-Theoretic Safe Exploration with Gaussian Processescited by 9
  5. 2024PACSBO: Probably approximately correct safe Bayesian optimizationcited by 8
  6. 2023A computationally lightweight safe learning algorithmcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Computationally lightweight classifiers with frequentist bounds on predictionscited by 1
  2. 2026Computationally efficient safe exploration in reinforcement learningcited by 0