Gilles Bareilles

Preprints

A. Bosák, A. Kliachkin, J. Lepšová, G. Bareilles, J. Mareček: Stochastic Penalty-Barrier Methods for Constrained Machine Learning. arXiv. 2026.

G. Bareilles*, W. Bouaziz*, J. Fageot*, E.-M. El-Mhamdi: Byzantine Machine Learning: MultiKrum and an optimal notion of robustness. arXiv. 2026.

G. Bareilles*, A. Gehret*, J. Aspman, J. Lepšová, J. Mareček: Deep Learning as the Disciplined Construction of Tame Objects. arXiv. 2025.

G. Bareilles*, J. Fageot*, L.-N. Hoang*, P. Blanchard, W. Bouaziz, S. Rouault, E.-M. El-Mhamdi: On Monotonicity in AI Alignment. arXiv. 2025.

Peer-reviewed journal articles

G. Bareilles, J. Aspman, J. Němeček, J. Mareček: Piecewise Polynomial Regression of Tame Functions via Integer Programming. Computer Aided Geometric Design. 2026.

G. Bareilles, F. Iutzeler, J. Malick: Harnessing structure in composite nonsmooth minimization. SIAM Journal on Optimization. 2023.

G. Bareilles, F. Iutzeler, J. Malick: Newton acceleration on manifolds identified by proximal-gradient methods. Mathematical Programming. 2022.

G. Bareilles, Y. Laguel, D. Grishchenko, F. Iutzeler, J. Malick. Randomized Progressive Hedging methods for Multi-stage Stochastic Programming. Annals of Operations Research. 2020.

G. Bareilles, F. Iutzeler. On the Interplay between Acceleration and Identification for the Proximal Gradient algorithm. Computational Optimization and Applications. 2020.

Peer-reviewed international conferences (with proceedings)

G. Bareilles*, W. Bouaziz*, J. Fageot*, E.-M. El-Mhamdi: Byzantine Machine Learning: MultiKrum and an optimal notion of robustness. PODC (Brief Announcement). 2026.

A. Kliachkin*, J. Lepšová*, G. Bareilles*, J. Mareček: Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks. ICLR. 2026. OpenReview

J. Fageot*, P. Blanchard*, G. Bareilles*, L.-N. Hoang: Generalizing while preserving monotonicity in comparison-based preference learning models. NeurIPS. 2025. OpenReview

Peer-reviewed international conference workshops (non-archival)

G. Bareilles*, W. Bouaziz*, J. Fageot*, E.-M. El-Mhamdi: Byzantine Machine Learning: MultiKrum and an optimal notion of robustness. ICLR 2026 Workshop Trustworthy AI. 2026. OpenReview

N. Hezbri, G. Bareilles, E.-M. El-Mhamdi: Dropout and the Outliers: Could Transformers Overcome Their Single Points of Failure? ICLR 2026 Workshop Sci4DL. 2026. OpenReview

G. Bareilles, J. Aspman, J. Němeček, J. Mareček: Piecewise Polynomial Regression of Tame Functions via Integer Programming. ICLR 2025 Workshop XAI4Science. 2025. OpenReview

A. Kliachkin, J. Lepšová, G. Bareilles, J. Mareček: humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems. Neurips COML Workshop 2025. 2025. OpenReview

Thesis

G. Bareilles. Structured nonsmooth optimization: proximal identification, fast local convergence, and applications. Ph.D. Thesis, Univ. Grenoble Alpes, defended December 2nd, 2022. Manuscript

Technical report

J. Aspman, G. Bareilles, V. Kungurtsev, J. Mareček, M. Takáč: Hybrid Methods in Polynomial Optimisation. arXiv. 2023.