Skip to main content

From FUnction-based TO MOdel-based automated probabilistic reasoning for DEep Learning

Searching for OpenAIRE data...

Publications

On the Benefits of Invariance in Neural Networks

Author(s): Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal, Benjamin Bloem-Reddy
Published in: Technical report Presented as poster at the NeurIPS 2019 Machine Learning with Guarantees Workshop., 2020
Publisher: Machine Learning
DOI: 10.48550/arxiv.2005.00178

PRISM-games 3.0 and 3.1

Author(s): Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Published in: Software, 2020
Publisher: n/a

DeepBayes

Author(s): Matthew Wicker
Published in: Software, 2022
Publisher: n/a

SafeDRL

Author(s): David Parker
Published in: Software, 2022
Publisher: n/a

Uncertify: Attacks Against Neural Network Certification

Author(s): Lorenz, Tobias; Kwiatkowska, Marta; Fritz, Mario
Published in: Technical report, under submission, 1, 2021
Publisher: Technical report - Under submission
DOI: 10.48550/arxiv.2108.11299

PRISM 4.7

Author(s): David Parker, Gethin Norman, Marta Kwiatkowska
Published in: Software, 2021
Publisher: n/a

Adversarial Robustness Guarantees for Gaussian Processes

Author(s): Andrea Patane, Arno Blaas, Luca Laurenti, Luca Cardelli, Stephen Roberts, Marta Kwiatkowska
Published in: 2021
Publisher: Technical report, https://arxiv.org/abs/2104.03180, under submission to journal

Strategy Synthesis for Zero-sum Neuro-symbolic Concurrent Stochastic Games

Author(s): Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Published in: Technical report, under submission, 2022
Publisher: arxiv

webppl-cognitive-agents

Author(s): Maciej Olejnik
Published in: Software and data, 2022
Publisher: n/a

Bayesian Inference with Certifiable Adversarial Robustness

Author(s): Matthew Wicker, Luca Laurenti, Andrea Patane, Zhuotong Chen, Zheng Zhang, Marta Kwiatkowska
Published in: Proceedings, International Conference on Artificial Intelligence and Statistics (AISTATS'21), 2021
Publisher: PMLR

Multi-Objective Controller Synthesis with Uncertain Human Preferences

Author(s): Shenghui Chen, Kayla Boggess, David Parker, Lu Feng
Published in: Proc. ACM/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS'22), 2022
Publisher: ACM/IEEE International Conference on Cyber-Physical Systems
DOI: 10.48550/arxiv.2105.04662

Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise

Author(s): Thom S. Badings, Alessandro Abate, Nils Jansen, David Parker, Hasan A. Poonawala, Marielle Stoelinga
Published in: Proc. 36th AAAI Conference on Artificial Intelligence (AAAI'22), 2022
Publisher: AAAI Press
DOI: 10.48550/arxiv.2110.12662

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

Author(s): Emanuele La Malfa, Marta Kwiatkowska
Published in: Proc. 36th AAAI Conference on Artificial Intelligence (AAAI'22), 2022
Publisher: Association for the Advancement of Artificial Intelligence
DOI: 10.48550/arxiv.2112.07605

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

Author(s): Hjalmar Wijk, Benjie Wang, Marta Kwiatkowska
Published in: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Publisher: International Joint Conferences on Artificial Intelligence
DOI: 10.48550/arxiv.2205.05793

Individual Fairness Guarantees for Neural Networks

Author(s): Elias Benussi, Andrea Patane, Matthew Wicker, Luca Laurenti, Marta Kwiatkowska
Published in: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Publisher: International Joint Conferences on Artificial Intelligence
DOI: 10.48550/arxiv.2205.05763

Certification of Iterative Predictions in Bayesian Neural Networks

Author(s): Matthew Wicker, Luca Laurenti, Andrea Patane, Nicola Paoletti, Alessandro Abate, Marta Kwiatkowska
Published in: 37th Conference on Uncertainty in Artificial Intelligence (UAI'21), 2021
Publisher: Association for Uncertainty in Artificial Intelligence (AUAI)

Safety and Robustness for Deep Learning with Provable Guarantees

Author(s): Marta Kwiatkowska
Published in: Proceedings, 35th IEEE/ACM International Conference on Automated Software Engineering (ASE ’20), 2020
Publisher: ACM

Sample complexity bounds for robustly learning decision lists against evasion attacks

Author(s): Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska and James Worrell
Published in: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Publisher: International Joint Conferences on Artificial Intelligence
DOI: 10.48550/arxiv.2205.06127

Verified Probabilistic Policies for Deep Reinforcement Learning

Author(s): Edoardo Bacci, David Parker
Published in: International Symposium NASA Formal Methods (NFM'22)., 2022
Publisher: Springer
DOI: 10.48550/arxiv.2201.03698

Finite-horizon Equilibria for Neuro-symbolic Concurrent Stochastic Games

Author(s): Rui Yan, Gabriel Santos, Xiaoming Duan, David Parker, Marta Kwiatkowska
Published in: Proc. 38th Conference on Uncertainty in Artificial Intelligence (UAI'22), 2022
Publisher: AUAI Press

Probabilistic Guarantees for Safe Deep Reinforcement Learning

Author(s): Edoardo Bacci, David Parker
Published in: Formal Modeling and Analysis of Timed Systems - 18th International Conference, FORMATS 2020, Vienna, Austria, September 1–3, 2020, Proceedings, 12288, 2020, Page(s) 231-248, ISBN 978-3-030-57627-1
Publisher: Springer International Publishing
DOI: 10.1007/978-3-030-57628-8_14

Multi-player Equilibria Verification for Concurrent Stochastic Games

Author(s): Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Published in: Proc. 17th International Conference on Quantitative Evaluation of SysTems (QEST'20), 2020
Publisher: Springer

On Correctness, Precision, and Performance in Quantitative Verification: QComp 2020 Competition Report

Author(s): Carlos E. Budde, Arnd Hartmanns, Michaela Klauck, Jan Kretinsky, David Parker, Tim Quatmann, Andrea Turrini and Zhen Zhang
Published in: Proc. 9th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation (ISoLA'20), 2020
Publisher: Springer

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions

Author(s): Benjie Wang, Clare Lyle, Marta Kwiatkowska
Published in: 30th International Joint Conference on Artificial Intelligence (IJCAI'21), 2021
Publisher: IJCAI

Tractable Uncertainty for Structure Learning

Author(s): Benjie Wang, Matthew Wicker, Marta Kwiatkowska
Published in: Proc. 39th International Conference on Machine Learning (ICML'22), 2022
Publisher: PMLR

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models

Author(s): Hannah Rose Kirk, yennie jun, Filippo Volpin, Haider Iqbal, Elias Benussi, Frederic Dreyer, Aleksandar Shtedritski, Yuki Asano
Published in: Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021
Publisher: PMLR

Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper)

Author(s): Marta Kwiatkowska
Published in: 30th International Conference on Concurrency Theory (CONCUR 2019), 2019
Publisher: Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik
DOI: 10.4230/lipics.concur.2019.1

Safety Guarantees for Iterative Predictions with Gaussian Processes

Author(s): Kyriakos Polymenakos, Luca Laurenti, Andrea Patane, Jan-Peter Calliess, Luca Cardelli, Marta Kwiatkowska, Alessandro Abate, Stephen Roberts
Published in: Proceedings, 59th IEEE Conference on Decision and Control (CDC), 2020
Publisher: IEEE

PRISM-games 3.0: Stochastic Game Verification with Concurrency, Equilibria and Time

Author(s): Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Published in: Computer Aided Verification - 32nd International Conference, CAV 2020, Los Angeles, CA, USA, July 21–24, 2020, Proceedings, Part II, 12225, 2020, Page(s) 475-487, ISBN 978-3-030-53290-1
Publisher: Springer International Publishing
DOI: 10.1007/978-3-030-53291-8_25

Assessing Robustness of Text Classification through Maximal Safe Radius Computation

Author(s): Emanuele La Malfa, Min Wu, Luca Laurenti, Benjie Wang, Anthony Hartshorn, Marta Kwiatkowska
Published in: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, Page(s) 2949-2968
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.266

Verifying Reinforcement Learning up to Infinity

Author(s): Edoardo Bacci, Mirco Giacobbe, David Parker
Published in: Proceedings, 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021
Publisher: IJCAI

Learning Dynamics and Generalization in Reinforcement Learning

Author(s): Clare Lyle, Mark Rowland, Will Dabney, Marta Kwiatkowska, Yarin Gal
Published in: Proc. 39th International Conference on Machine Learning (ICML'22), 2022
Publisher: PMLR

Correlated equilibria and fairness in concurrent stochastic games

Author(s): Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Published in: Tools and Algorithms for the Construction and Analysis of Systems - 28th International Conference, TACAS 2022, 2022, ISSN 0302-9743
Publisher: Springer

On Guaranteed Optimal Robust Explanations for NLP Models

Author(s): Emanuele La Malfa, Agnieszka Zbrzezny, Rhiannon Michelmore, Nicola Paoletti, Marta Kwiatkowska
Published in: Proceedings, 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021
Publisher: IJCAI

Invariant Causal Prediction for Block MDPs

Author(s): Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup
Published in: Proceedings of the 37th International Conference on Machine Learning (ICML), 2020
Publisher: PMLR 119

Probabilistic Safety for Bayesian Neural Networks

Author(s): Matthew Wicker, Luca Laurenti, Andrea Patane, Marta Kwiatkowska
Published in: Proceedings, 36th Conference on Uncertainty in Artificial Intelligence (UAI 2020), 2020
Publisher: PMLR

Adversarial Robustness Guarantees for Classification with Gaussian Processes

Author(s): Arno Blaas, Andrea Patane, Luca Laurenti, Luca Cardelli, Marta Kwiatkowska, Stephen Roberts
Published in: Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, 2020
Publisher: PMLR

Robustness Guarantees for Deep Neural Networks on Videos

Author(s): Min Wu, Marta Kwiatkowska
Published in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Page(s) 308-317, ISBN 978-1-7281-7168-5
Publisher: IEEE
DOI: 10.1109/cvpr42600.2020.00039

Automatic Verification and Strategy Synthesis for Zero-sum and Equilibria Properties of Concurrent Stochastic Games

Author(s): Gabriel Santos
Published in: PhD thesis, 2021
Publisher: University of Oxford

Formal Verification of Deep Reinforcement Learning Agents

Author(s): Edoardo Bacci
Published in: PhD thesis, 2022
Publisher: University of Birmingham

Modelling Human-Like Decision Making and Social Trust Using Probabilistic Programming

Author(s): Maciej Olejnik
Published in: PhD thesis (completed and examined, awaiting final approval for institutional release in ORA), 2022
Publisher: University of Oxford

On the Adversarial Robustness of Gaussian Processes

Author(s): Andrea Patane
Published in: PhD thesis, 2021
Publisher: University of Oxford

Robustness Evaluation of Deep Neural Networks with Provable Guarantees

Author(s): Min Wu
Published in: PhD thesis, 2020
Publisher: University of Oxford

Adversarial robustness of Bayesian neural networks

Author(s): Matthew Wicker
Published in: PhD thesis, 2022
Publisher: University of Oxford

A Language for Modeling and Optimizing Experimental Biological Protocols

Author(s): Luca Cardelli; Marta Kwiatkowska; Luca Laurenti
Published in: Computation, 9, 107, 2021, ISSN 2079-3197
Publisher: MDPI
DOI: 10.3390/computation9100107

Probabilistic model checking and autonomy

Author(s): Marta Kwiatkowska, Gethin Norman and David Parker
Published in: Annual Review of Control, Robotics, and Autonomous Systems, 5:1,, 2022, Page(s) 385-410, ISSN 2573-5144
Publisher: Annual Review of Control, Robotics, and Autonomous Systems
DOI: 10.1146/annurev-control-042820-010947

Rational verification: game-theoretic verification of multi-agent systems

Author(s): Abate, Alessandro; Gutierrez, Julian; Hammond, Lewis; Harrenstein, Paul; Kwiatkowska, Marta; Najib, Muhammad; Perelli, Giuseppe; Steeples, Thomas; Wooldridge, Michael
Published in: Appl Intell, 51, 2021, Page(s) 6569–6584, ISSN 0924-669X
Publisher: Kluwer Academic Publishers
DOI: 10.1007/s10489-021-02658-y