6 papers
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…
Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems
Pierre-Cyril Aubin-Frankowski, Yohann De Castro, Axel Parmentier +1
Many real-world decision problems require solving, again and again, combinatorial optimization instances drawn from a common distribution. A recent line of structured learning meth…
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…
Safely Learning Controlled Stochastic Dynamics
Luc Brogat-Motte, Alessandro Rudi, Riccardo Bonalli
We address the problem of safely learning controlled stochastic dynamics from discrete-time trajectory observations, ensuring system trajectories remain within predefined safe regi…
Dynamic Regret Reduces to Kernelized Static Regret
Andrew Jacobsen, Alessandro Rudi, Francesco Orabona +1
We study dynamic regret in online convex optimization, where the objective is to achieve low cumulative loss relative to an arbitrary benchmark sequence. By observing that competin…
Solving moment and polynomial optimization problems on Sobolev spaces
Didier Henrion, Alessandro Rudi
Using standard tools of harmonic analysis, we state and solve the problem of moments for non-negative measures supported on the unit ball of a Sobolev space of multivariate periodi…