Publications

Victor Boone, Cyrille Kone, Waris Radji, Odalric-Ambrym Maillard, Dorian Baudry (2026). Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling. NeurIPS 2026.

Romain Gautron, Jorge C. Berny Mier y Teran, Luis Fernando Delgado Muñoz, Santos Barrera Lemus, Eric Rahn, Fabio A. Castro Llanos, Christian Bunn, Salvador A. Gezan, Solène Pruvot-Woehl, Catherine Maina, Jane Jerono Cheserek, Jonny Alonso Castillo, Rosalío López Morgado, Edgardo Alpízar, Julio Alvarado, Josué Arevalo, Brahim Banda, Dorian Baudry, Mélanie Bordeaux, Elly Castro, Jeena Devasia, Elijah K. Gichuru, James Mwita Gimase, Chemutai Job Alunga, Nathan Aliel Kachiguma, Divya Kallingapuram Das, Jean-Baptiste Kayigamba, Tobias Kretzschmar, Suresh Kumar, Simon Martin Mvuyekure, Benit Mate, Hans Alexander Méndez Mendoza, Albertino Meza, Yonis Morales, Beatriz Moreno López, Paul Mulemangabo, Never Mwatsiya, Nayani Suryprakash Rao, Miftahur Rizqi Akbar, Ariana Karina Román Ruíz, Timothy Schilling, Godfrey Sseremba, Samson Tarusenga, Piet van Asten, Ari Wibowo, Tania Humphrey (2026). An international multilocation trial reveals genotype-by-environment interactions in Arabica coffee across climate gradients. Scientific Reports.

Djamel Rassem Lamouri, Dorian Baudry, Nicolas Gast (2026). The Bias of Nonlinear Two-Time-scale Stochastic Approximation under Constant Step-Sizes. Preprint.

Andrew Jacobsen, Dorian Baudry, Shinji Ito, Nicolò Cesa-Bianchi (2026). A Perturbation Approach to Unconstrained Linear Bandits. ICML 2026.

Dorian Baudry, Emmeran Johnson, Simon Vary, Ciara Pike-Burke, Patrick Rebeschini (2025). Does Stochastic Gradient really succeed for bandits?. NeurIPS 2025 Oral.

Xiaoqi Liu, Dorian Baudry, Julian Zimmert, Patrick Rebeschini, Arya Akhavan (2025). Non-stationary Bandit Convex Optimization: A Comprehensive Study. NeurIPS 2025.

Nathan Boyer, Dorian Baudry, Patrick Rebeschini (2025). Best-of-Both Worlds for linear contextual bandits with paid observations. Preprint.

Marius Potfer, Dorian Baudry, Hugo Richard, Vianney Perchet, Cheng Wan (2024). Improved learning rates in multi-unit uniform price auctions. NeurIPS 2024.

Nadav Merlis, Dorian Baudry, Vianney Perchet (2024). The Value of Reward Lookahead in Reinforcement Learning. NeurIPS 2024 Spotlight.

Dorian Baudry, Hugo Richard, Maria Cherifa, Clément Calauzènes, Vianney Perchet (2024). Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits. NeurIPS 2024.

Ziyad Benomar, Dorian Baudry, Vianney Perchet (2024). Lookback Prophet Inequalities. NeurIPS 2024.

Dorian Baudry, Nadav Merlis, Mathieu Benjamin Molina, Hugo Richard, Vianney Perchet (2024). Multi-Armed Bandits with Guaranteed Revenue per Arm. AISTATS 2024.

Romain Gautron, Dorian Baudry, Myriam Adam, Gatien N. Falconnier, Gerrit Hoogenboom, Brian King, Marc Corbeels (2024). A new adaptive identification strategy of best crop management with farmers. Field Crops Research.

Preprint PDF DOI

Dorian Baudry, Kazuya Suzuki, Junya Honda (2023). A General Recipe for the Analysis of Randomized Multi-Armed Bandit Algorithms. Preprint.

Dorian Baudry, Fabien Pesquerel, Rémy Degenne, Odalric-Ambrym Maillard (2023). Fast asymptotically optimal algorithms for non-parametric stochastic bandits. NeurIPS 2023.

Dorian Baudry (2022). Non-parametric algorithms for Multi-Armed Bandits. [PhD Thesis].

Marc Jourdan, Rémy Degenne, Dorian Baudry, Rianne de Heide, Emilie Kaufmann (2022). Top Two Algorithms Revisited. NeurIPS 2022.

Dorian Baudry, Yoan Russac, Emilie Kaufmann (2022). Efficient Algorithms for Extreme Bandits. AISTATS 2022.

Preprint PDF Video

Dorian Baudry, Patrick Saux, Odalric-Ambrym Maillard (2021). From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits. NeurIPS 2021.

Dorian Baudry, Yoan Russac, Olivier Cappé (2021). On Limited-Memory Subsampling Strategies for Bandits. ICML 2021.

Dorian Baudry, Romain Gautron, Emilie Kaufmann, Odalric-Ambrym Maillard (2021). Optimal Thompson Sampling strategies for support-aware CVaR bandits. ICML 2021.

Preprint PDF Code

Dorian Baudry, Emilie Kaufmann, Odalric-Ambrym Maillard (2020). Sub-sampling for Efficient Non-Parametric Bandit Exploration. NeurIPS 2020 Spotlight.