Picture for Mahyar Fazlyab

Mahyar Fazlyab

Domain Adaptive Safety Filters via Deep Operator Learning

Add code
Oct 18, 2024
Viaarxiv icon

Compositional Curvature Bounds for Deep Neural Networks

Add code
Jun 07, 2024
Viaarxiv icon

Provable Bounds on the Hessian of Neural Networks: Derivative-Preserving Reachability Analysis

Add code
Jun 06, 2024
Viaarxiv icon

Gradient-Regularized Out-of-Distribution Detection

Add code
Apr 18, 2024
Viaarxiv icon

Actor-Critic Physics-informed Neural Lyapunov Control

Add code
Mar 13, 2024
Viaarxiv icon

Verification-Aided Learning of Neural Network Barrier Functions with Termination Guarantees

Add code
Mar 12, 2024
Viaarxiv icon

Learning Performance-Oriented Control Barrier Functions Under Complex Safety Constraints and Limited Actuation

Add code
Jan 11, 2024
Viaarxiv icon

Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization

Add code
Sep 29, 2023
Viaarxiv icon

Certified Invertibility in Neural Networks via Mixed-Integer Programming

Add code
Jan 27, 2023
Viaarxiv icon

Automated Reachability Analysis of Neural Network-Controlled Systems via Adaptive Polytopes

Add code
Dec 14, 2022
Viaarxiv icon