MA
Marc Abeille
cs.LGstat.MLmath.OCcs.GTcs.AImath.STq-fin.PMstat.TH
On Valency
published · living versionsW_5233a9ft·v1 · currentpublished
Does LinUCB Need Valid Confidence Sets?
with Ahmed Ben Yahmed, David Janz, Clément Calauzènes
1 version
Preprints & journals
22 papers in the corpus · 2016–2026On the Complexity of Preference-Based Bandits2609.39351v1 · Ahmed Ben Yahmed, Marc Abeille (FAIRPLAY), Cl'ement Calauzenes (FAIRPLAY)2026 · 0 citationsNeurIPS 2026 - Fortieth Annual Conference on Neural Information Processing Systems, Dec 2026, Sydney (AUSTRALIA), Australia
Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead2609.11807v2 · Corentin Pla, Hugo Richard, Marc Abeille et al.2026 · 0 citationsarXiv
Minimax PAC Bounds for Learning in Exogenous Contextual MDPs2606.25170v3 · Corentin Pla, Hugo Richard, Marc Abeille et al.2026 · 0 citationsarXiv
Variance-sensitive Thompson sampling for generalised linear bandits, revisited2606.00431v1 · Tom Perneczky, Marc Abeille, David Janz2026 · 0 citationsarXiv
On the Hardness of Reinforcement Learning with Transition Look-Ahead2510.19372v3 · Corentin Pla, Hugo Richard, Marc Abeille et al.2025 · 0 citationsarXiv
Multi-Armed Bandits with Minimum Aggregated Revenue Constraints2510.12523v1 · Ahmed Ben Yahmed, Hafedh El Ferchichi, Marc Abeille et al.2025 · 0 citationsarXiv
When and why randomised exploration works (in linear bandits)2502.08870v2 · Marc Abeille, David Janz, Ciara Pike-Burke2025 · 0 citationsarXiv
Near-continuous time Reinforcement Learning for continuous state-action spaces2309.02815v1 · Lorenzo Croissant (CEREMADE), Marc Abeille, Bruno Bouchard (CEREMADE)2023 · 1 citationarXiv
Diffusive limit approximation of pure jump optimal ergodic control problems2209.15284v1 · Marc Abeille, Bruno Bouchard (CEREMADE), Lorenzo Croissant (CEREMADE)2022 · 0 citationsarXiv
Jointly Efficient and Optimal Algorithms for Logistic Bandits2201.01985v2 · Louis Faury, Marc Abeille, Kwang-Sung Jun et al.2022 · 0 citationsarXiv
Diffusive limit approximation of pure-jump optimal stochastic control problems2106.12848v2 · Marc Abeille, Bruno Bouchard, Lorenzo Croissant2021 · 4 citationsarXiv
Regret Bounds for Generalized Linear Bandits under Parameter Drift2103.05750v1 · Louis Faury, Yoan Russac, Marc Abeille et al.2021 · 2 citationsarXiv
Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits2010.12642v2 · Marc Abeille, Louis Faury, Cl'ement Calauzenes2020 · 6 citationsarXiv
Real-Time Optimisation for Online Learning in Auctions2010.10070v1 · Lorenzo Croissant, Marc Abeille, Cl'ement Calauzenes2020 · 3 citationsarXiv
Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation2007.06482v1 · Marc Abeille, Alessandro Lazaric2020 · 17 citationsarXiv
Improved Optimistic Algorithms for Logistic Bandits2002.07530v2 · Louis Faury, Marc Abeille, Cl'ement Calauzenes et al.2020 · 22 citationsarXiv
Thompson Sampling in Non-Episodic Restless Bandits1910.05654v1 · Young Hun Jung, Marc Abeille, Ambuj Tewari2019 · 8 citationsarXiv
Thresholding at the monopoly price: an agnostic way to improve bidding strategies in revenue-maximizing auctions1808.06979v5 · Thomas Nedelec, Marc Abeille, Cl'ement Calauzenes et al.2018 · 3 citationsarXiv
Explicit shading strategies for repeated truthful auctions1805.00256v3 · Marc Abeille, Cl'ement Calauzenes, Noureddine El Karoui et al.2018 · 5 citationsarXiv
Thompson Sampling for Linear-Quadratic Control Problems1703.08972v1 · Marc Abeille, Alessandro Lazaric2017 · 35 citationsarXiv
Linear Thompson Sampling Revisited1611.06534v3 · Marc Abeille, Alessandro Lazaric2016 · 160 citationsarXivon Valency
LQG for portfolio optimization1611.00997v2 · M. Abeille, E. Serie, A. Lazaric et al.2016 · 10 citationsarXiv
Career total: 28 works. 22 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.