Search Results for author: Alexandre Megretski

Found 5 papers, 1 papers with code

Tactics on Refining Decision Boundary for Improving Certification-based Robust Training

no code implementations29 Sep 2021 Wang Zhang, Lam M. Nguyen, Subhro Das, Pin-Yu Chen, Sijia Liu, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng

In verification-based robust training, existing methods utilize relaxation based methods to bound the worst case performance of neural networks given certain perturbation.

Efficient Certification for Probabilistic Robustness

no code implementations29 Sep 2021 Victor Rong, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng

Recent developments on the robustness of neural networks have primarily emphasized the notion of worst-case adversarial robustness in both verification and robust training.

Adversarial Robustness

Robust Online Control with Model Misspecification

no code implementations16 Jul 2021 Xinyi Chen, Udaya Ghai, Elad Hazan, Alexandre Megretski

We study online control of an unknown nonlinear dynamical system that is approximated by a time-invariant linear system with model misspecification.

Robust Deep Reinforcement Learning through Adversarial Loss

2 code implementations NeurIPS 2021 Tuomas Oikarinen, Wang Zhang, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng

To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against $l_p$-norm bounded adversarial attacks.

Adversarial Attack Atari Games +2

Convex Parameterizations and Fidelity Bounds for Nonlinear Identification and Reduced-Order Modelling

no code implementations23 Jan 2017 Mark M. Tobenkin, Ian R. Manchester, Alexandre Megretski

Model instability and poor prediction of long-term behavior are common problems when modeling dynamical systems using nonlinear "black-box" techniques.

Cannot find the paper you are looking for? You can Submit a new open access paper.