activity
20192022
most citedOn the Benefits of Invariance in Neural Networks

17 citations · 49 across the 11 of their papers we have counts for

collaborators

23 papers

cs.AI2022

Bayesian Network Models of Causal Interventions in Healthcare Decision Making: Literature Review and Software Evaluation

Artem Velikzhanin, Benjie Wang, Marta Kwiatkowska

This report summarises the outcomes of a systematic literature search to identify Bayesian network models used to support decision making in healthcare. After describing the search…

cs.LG2022

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.…

cs.LG2022

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…

cs.AI2022

Robustness Guarantees for Credal Bayesian Networks via Constraint Relaxation over Probabilistic Circuits

Hjalmar Wijk, Benjie Wang, Marta Kwiatkowska

In many domains, worst-case guarantees on the performance (e.g., prediction accuracy) of a decision function subject to distributional shifts and uncertainty about the environment…

cs.CL20222 cited

The King is Naked: on the Notion of Robustness for Natural Language Processing

Emanuele La Malfa, Marta Kwiatkowska

There is growing evidence that the classical notion of adversarial robustness originally introduced for images has been adopted as a de facto standard by a large part of the NLP re…

cs.LG20212 cited

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…