4 papers
Leveraging Similarities in Multi-Armed Bandits
Khaled Eldowa, Thibaud Rahier, Augustin Cablant +2
In many online learning and bandit problems, the actions we consider possess inherent similarities--for instance because they share latent traits, tags, or hierarchical structure.…
Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
Pierre Boudart, Pierre Gaillard, Alessandro Rudi
We study reinforcement learning for episodic Markov Decision Processes (MDPs) whose transitions are modelled by a multinomial logistic (MNL) model. Existing algorithms for MNL mixt…
Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm
Pierre Boudart, Pierre Gaillard, Alessandro Rudi
We consider the multinomial logistic bandit problem in which a learner interacts with an environment by selecting actions to maximize expected rewards based on probabilistic feedba…
Structured Prediction in Online Learning
Pierre Boudart, Alessandro Rudi, Pierre Gaillard
We study a theoretical and algorithmic framework for structured prediction in the online learning setting. The problem of structured prediction, i.e. estimating function where the…