37 citations · 147 across the 28 of their papers we have counts for
16 papers · 1 filter
Probabilistic Reach-Avoid for Bayesian Neural Networks
Matthew Wicker, Luca Laurenti, Andrea Patane +3
Model-based reinforcement learning seeks to simultaneously learn the dynamics of an unknown stochastic environment and synthesise an optimal policy for acting in it. Ensuring the s…
Adversarial Robustness Certification for Bayesian Neural Networks
Matthew Wicker, Andrea Patane, Luca Laurenti +1
We study the problem of certifying the robustness of Bayesian neural networks (BNNs) to adversarial input perturbations. Given a compact set of input points $T \subseteq \mathbb{R}…
Robustness of Unsupervised Representation Learning without Labels
Aleksandar Petrov, Marta Kwiatkowska
Unsupervised representation learning leverages large unlabeled datasets and is competitive with supervised learning. But non-robust encoders may affect downstream task robustness.…
When are Local Queries Useful for Robust Learning?
Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska +1
Distributional assumptions have been shown to be necessary for the robust learnability of concept classes when considering the exact-in-the-ball robust risk and access to random ex…
Learning Dynamics and Generalization in Reinforcement Learning
Clare Lyle, Mark Rowland, Will Dabney +2
Solving a reinforcement learning (RL) problem poses two competing challenges: fitting a potentially discontinuous value function, and generalizing well to new observations. In this…
Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks
Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska +1
A fundamental problem in adversarial machine learning is to quantify how much training data is needed in the presence of evasion attacks. In this paper we address this issue within…
Tractable Uncertainty for Structure Learning
Benjie Wang, Matthew Wicker, Marta Kwiatkowska
Bayesian structure learning allows one to capture uncertainty over the causal directed acyclic graph (DAG) responsible for generating given data. In this work, we present Tractable…
Certification of Iterative Predictions in Bayesian Neural Networks
Matthew Wicker, Luca Laurenti, Andrea Patane +3
We consider the problem of computing reach-avoid probabilities for iterative predictions made with Bayesian neural network (BNN) models. Specifically, we leverage bound propagation…
Adversarial Robustness Guarantees for Gaussian Processes
Andrea Patane, Arno Blaas, Luca Laurenti +3
Gaussian processes (GPs) enable principled computation of model uncertainty, making them attractive for safety-critical applications. Such scenarios demand that GP decisions are no…
Bayesian Inference with Certifiable Adversarial Robustness
Matthew Wicker, Luca Laurenti, Andrea Patane +3
We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Netwo…
On the Benefits of Invariance in Neural Networks
Clare Lyle, Mark van der Wilk, Marta Kwiatkowska +2
Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in de…
Probabilistic Safety for Bayesian Neural Networks
Matthew Wicker, Luca Laurenti, Andrea Patane +1
We study probabilistic safety for Bayesian Neural Networks (BNNs) under adversarial input perturbations. Given a compact set of input points, , we study t…
Invariant Causal Prediction for Block MDPs
Amy Zhang, Clare Lyle, Shagun Sodhani +5
Generalization across environments is critical to the successful application of reinforcement learning algorithms to real-world challenges. In this paper, we consider the problem o…
Safety Guarantees for Planning Based on Iterative Gaussian Processes
Kyriakos Polymenakos, Luca Laurenti, Andrea Patane +5
Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step p…
Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Control
Rhiannon Michelmore, Matthew Wicker, Luca Laurenti +3
Deep neural network controllers for autonomous driving have recently benefited from significant performance improvements, and have begun deployment in the real world. Prior to thei…
On the Hardness of Robust Classification
Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska +1
It is becoming increasingly important to understand the vulnerability of machine learning models to adversarial attacks. In this paper we study the feasibility of robust learning f…