Publications

Johnson, E. et al. (2025) “Stochastic Shortest Path with Sparse Adversarial Costs.”
Boyer, N., Baudry, D. and Rebeschini, P. (2025) “Best-of-Both Worlds for linear contextual bandits with paid observations”, arXiv.
Aminian, G. et al. (2025) “Generalization and robustness of the tilted empirical risk”, in Proceedings of the 42nd International Conference on Machine Learning. PMLR, pp. 1419–1461.
Baudry, D. et al. (2025) “Does stochastic gradient really succeed for bandits?”, in.
Kilian, V., Cortinovis, S. and Caron, F. (2025) “Anytime-valid, Bayes-assisted, prediction-powered inference”, in. Neural Information Processing Systems Foundation.
Alfano, C. et al. (2025) “Meta-Learning Objectives for Preference Optimization”, in.