alphaFeedback
CV

Claire Vernade

cs.LGstat.MLcs.AImath.OCmath.PRcs.DScs.IRcs.ROcs.SImath.ST

On Valency

published · living versions
W_t6szp3tn·v1 · currentpublished
Gaussian Distillation of Flow Policies
with Youssef Saied, Ziyad Sheebaelhamd, François Fleuret
1 version
W_8enbzvq4·v1published

Preprints & journals

37 papers in the corpus · 2015–2026
Learning from a Bandit Learner2610.26103v1 · Michela Petriconi, Nicolas Menet, Claire Vernade2026 · 0 citationsarXivon Valency
Foundations of Reinforcement Learning and Control:Connections and New Perspectives2608.02433v1 · Claire Vernade, Onno Eberhard, Martha White et al.2026 · 0 citationsarXiv
To Retain or to Adapt? Generalizing Continual Learning2607.05609v2 · Giulia Lanzillotta, Mandana Samiei, Doina Precup et al.2026 · 0 citationsTransactions on Machine Learning Research, 2026
Commit to the Bit: Reactive Reinforcement Learning Done Right2605.28276v2 · Onno Eberhard, Claire Vernade, Michael Muehlebach2026 · 0 citationsarXiv
Tight Sample Complexity Bounds for Entropic Best Policy Identification2605.13717v2 · Amer Essakine, Claire Vernade2026 · 0 citationsProceedings of the 39th Conference on Learning Theory (COLT 2026), Proceedings of Machine Learning Research 336:2339-2398, 2026
Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation2605.12000v3 · Ziyad Sheebaelhamd, Luca Viano, Volkan Cevher et al.2026 · 0 citationsarXiv
Non-Stationary Lipschitz Bandits2505.18871v2 · Nicolas Nguyen, Solenne Gaucher, Claire Vernade2025 · 0 citationsNeurIPS 2025
Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning2505.05226v2 · Amir Rezaei Balef, Claire Vernade, Katharina Eggensperger2025 · 0 citationsarXiv
Partially Observable Reinforcement Learning with Memory Traces2503.15200v2 · Onno Eberhard, Michael Muehlebach, Claire Vernade2025 · 0 citationsarXiv
Quantization-Free Autoregressive Action Transformer2503.14259v3 · Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach et al.2025 · 0 citations39th Conference on Neural Information Processing Systems, 2025
Clustered KL-barycenter design for policy evaluation2503.02735v1 · Simon Weissmann, Till Freihaut, Claire Vernade et al.2025 · 0 citationsarXiv
Efficient Risk-sensitive Planning via Entropic Risk Measures2502.20423v2 · Alexandre Marthe (ENS de Lyon, UMPA-ENSL), Samuel Bounan et al.2025 · 0 citationsarXiv
Variational Bayes Portfolio Construction2411.06192v1 · Nicolas Nguyen, James Ridgway, Claire Vernade2024 · 0 citationsarXiv
Online Decision Deferral under Budget Constraints2409.20489v1 · Mirabel Reid, Tom Suhr, Claire Vernade et al.2024 · 0 citationsarXiv
A Pontryagin Perspective on Reinforcement Learning2405.18100v3 · Onno Eberhard, Claire Vernade, Michael Muehlebach2024 · 0 citationsarXiv
Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits2402.05878v2 · Nicolas Nguyen, Imad Aouali, Andr'as Gyorgy et al.2024 · 0 citationsInternational Conference on Artificial Intelligence and Statistics (AISTATS 2025)
Beyond Average Return in Markov Decision Processes2310.20266v2 · Alexandre Marthe (ENS de Lyon, UMPA-ENSL), Aur'elien Garivier (UMPA-ENSL (MC2)) et al.2023 · 0 citationsarXiv
POMRL: No-Regret Learning-to-Plan with Increasing Horizons2212.14530v1 · Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue et al.2022 · 0 citationsarXiv
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms2202.13001v6 · MohammadJavad Azizi, Thang Duong, Yasin Abbasi-Yadkori et al.2022 · 1 citationarXiv
EigenGame Unloaded: When playing games is better than optimizing2102.04152v2 · Ian Gemp, Brian McWilliams, Claire Vernade et al.2021 · 4 citationsarXiv
Asymptotically Optimal Information-Directed Sampling2011.05944v4 · Johannes Kirschner, Tor Lattimore, Claire Vernade et al.2020 · 13 citationsarXiv
The Elliptical Potential Lemma Revisited2010.10182v1 · Alexandra Carpentier, Claire Vernade, Yasin Abbasi-Yadkori2020 · 4 citationsarXiv
EigenGame: PCA as a Nash Equilibrium2010.00554v2 · Ian Gemp, Brian McWilliams, Claire Vernade et al.2020 · 11 citationsarXiv
Stochastic bandits with arm-dependent delays2006.10459v1 · Anne Gael Manegueu, Claire Vernade, Alexandra Carpentier et al.2020 · 14 citationsarXiv
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting2006.10460v3 · Ilja Kuzborskij, Claire Vernade, Andr'as Gyorgy et al.2020 · 12 citationsarXiv
Non-Stationary Delayed Bandits with Intermediate Observations2006.02119v2 · Claire Vernade, Andras Gyorgy, Timothy Mann2020 · 7 citationsarXiv
Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling1912.03074v1 · Cindy Trinh, Emilie Kaufmann, Claire Vernade et al.2019 · 15 citationsarXiv
Weighted Linear Bandits for Non-Stationary Environments1909.09146v2 · Yoan Russac (DI-ENS, VALDA), Claire Vernade et al.2019 · 59 citationsNeurIPS 2019 - 33rd Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada
Linear Bandits with Stochastic Delayed Feedback1807.02089v3 · Claire Vernade, Alexandra Carpentier, Tor Lattimore et al.2018 · 26 citationsarXiv
Max K-armed bandit: On the ExtremeHunter algorithm and beyond1707.08820v1 · Mastane Achab, Stephan Cl'emencon, Aur'elien Garivier et al.2017 · 58 citationsarXiv
Stochastic Bandit Models for Delayed Conversions1706.09186v3 · Claire Vernade, Olivier Capp'e, Vianney Perchet2017 · 44 citationsarXiv
Sparse Stochastic Bandits1706.01383v1 · Joon Kwon, Vianney Perchet, Claire Vernade2017 · 4 citationsarXiv
Bernoulli Rank-11 Bandits for Click Feedback1703.06513v1 · Sumeet Katariya, Branislav Kveton, Csaba Szepesv'ari et al.2017 · 72 citationsarXiv
Stochastic Rank-1 Bandits1608.03023v3 · Sumeet Katariya, Branislav Kveton, Csaba Szepesvari et al.2016 · 7 citationsarXiv
Multiple-Play Bandits in the Position-Based Model1606.02448v1 · Paul Lagr'ee (UP11, LRI), Claire Vernade (LTCI) et al.2016 · 38 citationsarXivon Valency
Sequential ranking under random semi-bandit feedback1603.01450v2 · Hossein Vahabi, Paul Lagr'ee, Claire Vernade et al.2016 · 0 citationsarXiv
Learning From Missing Data Using Selection Bias in Movie Recommendation1509.09130v1 · Claire Vernade (LTCI), Olivier Capp'e (LTCI)2015 · 5 citationsarXiv
Career total: 41 works. 37 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.