activity
20172021
most citedApproximate Supermodularity of Kalman Filter Sensor Selection

35 citations · 54 across the 6 of their papers we have counts for

collaborators

19 papers

stat.ML20211 cited

Adversarial Robustness with Semi-Infinite Constrained Learning

Alexander Robey, Luiz F. O. Chamon, George J. Pappas +2

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. Wh…

cs.LG2021

Towards Safe Continuing Task Reinforcement Learning

Miguel Calvo-Fullana, Luiz F. O. Chamon, Santiago Paternain

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed,…

cs.LG2020

Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning

Luiz F. O. Chamon, Santiago Paternain, Alejandro Ribeiro

Prediction credibility measures, in the form of confidence intervals or probability distributions, are fundamental in statistics and machine learning to characterize model robustne…

cs.LG2020

Probably Approximately Correct Constrained Learning

Luiz F. O. Chamon, Alejandro Ribeiro

As learning solutions reach critical applications in social, industrial, and medical domains, the need to curtail their behavior has become paramount. There is now ample evidence t…

cs.LG2020

Graphon Neural Networks and the Transferability of Graph Neural Networks

Luana Ruiz, Luiz F. O. Chamon, Alejandro Ribeiro

Graph neural networks (GNNs) rely on graph convolutions to extract local features from network data. These graph convolutions combine information from adjacent nodes using coeffici…

eess.SY2020

Risk-Constrained Linear-Quadratic Regulators

Anastasios Tsiamis, Dionysios S. Kalogerias, Luiz F. O. Chamon +2

We propose a new risk-constrained reformulation of the standard Linear Quadratic Regulator (LQR) problem. Our framework is motivated by the fact that the classical (risk-neutral) L…