Safe Convex Learning under Uncertain Constraints
Not on the map. Why?
Abstract (arXiv)
We address the problem of minimizing a convex smooth function f(x) over a compact polyhedral set D given a stochastic zeroth-order constraint feedback model. This problem arises in safety-critical machine learning applications, such as personalized medicine and robotics. In such cases, one needs to ensure constraints are satisfied while exploring the decision space to find optimum of the loss function. We propose a new variant of the Frank-Wolfe algorithm, which applies to the case of uncertain linear constraints. Using robust optimization, we provide the convergence rate of the algorithm while guaranteeing feasibility of all iterates, with high probability.
Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Mar 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 1; 2023: 5; 2024: 4; 2025: 0; 2026: 1.
17 papers.
Sort:
By area:
- 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
- 2021DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learningcited by 34
- 2024Diffusion Models as Constrained Samplers for Optimization with Unknown Constraintscited by 33
- 2021An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraintscited by 29
- 2023Multi-channel Autobidding with Budget and ROI Constraintscited by 14
- 2021Safe Online Convex Optimization with Unknown Linear Safety Constraintscited by 13
- 2021Learning to Persuade on the Fly: Robustness Against Ignorancecited by 12
- 2022Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learningcited by 11
- 2023Directional Optimism for Safe Linear Banditscited by 8
- 2023Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problemscited by 4
- 2023Price of Safety in Linear Best Arm Identificationcited by 4
- 2023The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedbackcited by 3
5 more
- 2024Online Learning with Unknown Constraintscited by 2
- 2021Safe Linear Leveling Banditscited by 1
- 2024Optimistic Safety for Online Convex Optimization with Unknown Linear Constraintscited by 1
- 2024Safe Online Convex Optimization with Multi-Point Feedbackcited by 0
- 2026Constrained Online Learning with Noisy Constraint Valuescited by 0
- 2026Constrained Online Learning with Noisy Constraint Values7 Sep 2026
- 2024Safe Online Convex Optimization with Multi-Point Feedback16 Jul 2024
- 2024Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints9 Mar 2024
- 2024Online Learning with Unknown Constraints6 Mar 2024
- 2024Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints28 Feb 2024
- 2023Price of Safety in Linear Best Arm Identification15 Sep 2023
- 2023Directional Optimism for Safe Linear Bandits29 Aug 2023
- 2023The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback1 May 2023
- 2023Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems23 Feb 2023
- 2023Multi-channel Autobidding with Budget and ROI Constraints3 Feb 2023
- 2022Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning21 Jul 2022
- 2021Safe Linear Leveling Bandits13 Dec 2021
5 more
- 2021DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning1 Dec 2021
- 2021Safe Online Convex Optimization with Unknown Linear Safety Constraints14 Nov 2021
- 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review26 Jul 2021
- 2021Learning to Persuade on the Fly: Robustness Against Ignorance19 Feb 2021
- 2021An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints10 Feb 2021
- 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
- 2021DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learningcited by 34
- 2021An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraintscited by 29
- 2023Multi-channel Autobidding with Budget and ROI Constraintscited by 14
- 2021Safe Online Convex Optimization with Unknown Linear Safety Constraintscited by 13
- 2021Learning to Persuade on the Fly: Robustness Against Ignorancecited by 12
- 2022Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learningcited by 11
- 2023Directional Optimism for Safe Linear Banditscited by 8
- 2023Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problemscited by 4
- 2023Price of Safety in Linear Best Arm Identificationcited by 4
- 2023The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedbackcited by 3
- 2024Online Learning with Unknown Constraintscited by 2
12 most cited of 16 All 16 (JSON)
- 2026Constrained Online Learning with Noisy Constraint Values7 Sep 2026
- 2024Safe Online Convex Optimization with Multi-Point Feedback16 Jul 2024
- 2024Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints9 Mar 2024
- 2024Online Learning with Unknown Constraints6 Mar 2024
- 2023Price of Safety in Linear Best Arm Identification15 Sep 2023
- 2023Directional Optimism for Safe Linear Bandits29 Aug 2023
- 2023The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback1 May 2023
- 2023Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems23 Feb 2023
- 2023Multi-channel Autobidding with Budget and ROI Constraints3 Feb 2023
- 2022Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning21 Jul 2022
- 2021Safe Linear Leveling Bandits13 Dec 2021
- 2021DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning1 Dec 2021
12 newest of 16 All 16 (JSON)