| 2026 | COLT | Self-Concordant Perturbations for Linear Bandits. | Lucas Lvy, Jean-Lou Valeau, Arya Akhavan, Patrick Rebeschini |
| 2026 | COLT | On-Average Stability of Multipass Preconditioned SGD and Effective Dimension. | Simon Vary, Tyler Farghly, Ilja Kuzborskij, Patrick Rebeschini |
| 2025 | AISTATS | Robust Gradient Descent for Phase Retrieval. | Alex Buna, Patrick Rebeschini |
| 2025 | AISTATS | Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization. | Simon Vary, David Martnez-Rubio, Patrick Rebeschini |
| 2025 | ICLR | Learning mirror maps in policy mirror descent. | Carlo Alfano, Sebastian Rene Towers, Silvia Sapora, Chris Lu, Patrick Rebeschini |
| 2024 | AISTATS | Generalization Bounds for Label Noise Stochastic Gradient Descent. | Jung Eun Huh, Patrick Rebeschini |
| 2024 | ICLR | Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity. | Emmeran Johnson, Ciara Pike-Burke, Patrick Rebeschini |
| 2021 | AISTATS | Hadamard Wirtinger Flow for Sparse Phase Retrieval. | Fan Wu, Patrick Rebeschini |
| 2020 | ICML | Decentralised Learning with Random Features and Distributed Gradient Descent. | Dominic Richards, Patrick Rebeschini, Lorenzo Rosasco |
| 2016 | CISS | Decay of correlation in network flow problems. | Patrick Rebeschini, Sekhar Tatikonda |
| 2015 | COLT | Fast Mixing for Discrete Point Processes. | Patrick Rebeschini, Amin Karbasi |