Luiz Chamon
Luiz Chamon studies machine learning under constraints. His research connects optimization and control to requirements such as robustness and safe decision-making. Chamon and Alejandro Ribeiro coauthored Probably Approximately Correct Constrained Learning. The NeurIPS 2020 paper addresses operational requirements for AI systems. He coauthored work on adversarial robustness with constrained learning and on safe reinforcement-learning policies through primal-dual methods. These are mathematical studies with model conditions. Chamon’s paper Solving Differential Equations with Constrained Learning was accepted at ICLR 2025. His work also includes approximately equivariant networks and statistical equality constraints.
- Works
- 81
- Citations
- 1,072
- h-index
- 16
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
2020
Constrained learning theory
Chamon and Alejandro Ribeiro coauthored Probably Approximately Correct Constrained Learning. The NeurIPS 2020 paper addresses operational requirements for AI systems.
-
2021–2023
Robustness and safe policies
He coauthored work on adversarial robustness with constrained learning and on safe reinforcement-learning policies through primal-dual methods. These are mathematical studies with model conditions.
-
2025
Learning and differential equations
Chamon’s paper Solving Differential Equations with Constrained Learning was accepted at ICLR 2025. His work also includes approximately equivariant networks and statistical equality constraints.
Sources and credits
Photo: ELLIS profile; creator not stated. License: Not stated by source. Source: ellis.eu. Cropped to a square and resized. Ask us to remove or replace this photo.