[Google Scholar]

2025.
On Using Certified Training towards Empirical Robustness.
A. De Palma*, S. Durand*, Z. Chihani, F. Terrier, C. Urban.
Transactions on Machine Learning Research (TMLR), 2025. [arXiv]

Robustness to Perturbations in the Frequency Domain: Neural Network Verification and Certified Training.
H. Hanspal, A. De Palma, A. Lomuscio.
WACV 2025 Workshop on Out-of-Label Hazards in Autonomous Driving. [CVF]

2024.
Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation.
B. Batten, Y. Zheng, A. De Palma, P. Kouvaros, A. Lomuscio.
European Conference on Artificial Intelligence (ECAI), 2024. [arXiv]

Early Burst Suppression Similarity Association with Structural Brain Injury Severity on MRI After Cardiac Arrest.
S. Shivdat, T. Zhan, A. De Palma, W.L. Zheng, P. Krishnamurthy, E. Paneerselvam, S. Snider, M. Bevers, U.M. O’Reilly, J. Woo Lee, M.B. Westover, E. Amorim.
Neurocritical Care, 2024. [Springer]

Verified Neural Compressed Sensing.
R. Bunel*, K. Dvijotham*, M. P. Kumar*, A. De Palma, R. Stanforth.
arXiv:2405.04260. [arXiv]

Expressive Losses for Verified Robustness via Convex Combinations.
A. De Palma, R. Bunel, K. Dvijotham, M. P. Kumar, R. Stanforth, A. Lomuscio.
International Conference on Learning Representations (ICLR), 2024. [OpenReview]

Scaling the Convex Barrier with Sparse Dual Algorithms.
A. De Palma, H.S. Behl, R. Bunel, P. H.S. Torr, M. P. Kumar.
Journal of Machine Learning Research (JMLR), 2024. [arXiv]

2023.
Efficient Neural Network Verification and Training.
PhD thesis, University of Oxford. [ORA]

2022.
In Defense of the Unitary Scalarization for Deep Multi-Task Learning.
V. Kurin*, A. De Palma*, I. Kostrikov, S. Whiteson,  M. P. Kumar.
Neural Information Processing Systems (NeurIPS), 2022. [arXiv]

IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound.
A. De Palma, R. Bunel, K. Dvijotham, M. P. Kumar, R. Stanforth.
ICML 2022 Workshop on Formal Verification of Machine Learning, best paper award. [arXiv]

2021.
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition.
A. De Palma, R. Bunel, A. Desmaison, K. Dvijotham, P. Kohli, P. H.S. Torr, M. P. Kumar.
arXiv:2104.06718. [arXiv]

Scaling the Convex Barrier with Active Sets.
A. De Palma*, H.S. Behl*, R. Bunel, P. H.S. Torr, M. P. Kumar.
International Conference on Learning Representations (ICLR), 2021. [OpenReview]

2020.
Lagrangian Decomposition for Neural Network Verification.
R. Bunel*, A. De Palma*, A. Desmaison, K. Dvijotham, P. Kohli, P. H.S. Torr, M. P. Kumar.
Conference on Uncertainty in Artificial Intelligence (UAI), 2020. [arXiv]

2018.
Sampling Acquisition Functions for Batch Bayesian Optimization.
A. De Palma, C. Dünner, T. Parnell, A. Anghel, H. Pozidis.
NeurIPS BNP 2018 workshop. [arXiv]

Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms.
A. Anghel, N. Papandreou, T. Parnell, A. De Palma, H. Pozidis.
NeurIPS SysML 2018 workshop. [arXiv]

Communication-avoiding minimum cuts and connected components.
L. Gianinazzi, P. Kalvoda, A. De Palma, M. Besta, T. Hoefler.
ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, 2018.

2017.
Distributed Stratified Locality Sensitive Hashing for critical event prediction in the cloud.
A. De Palma, E. Hemberg, U. O’Reilly.
NeurIPS ML4H 2017 workshop, travel award winner. [arXiv]

(* indicates joint first authorship)