36:33
published on November 27, 2023
Monte Carlo guided Diffusion for Bayesian linear inverse problems
By Sylvain Le Corff
Multi-armed bandits and beyond
Appears in collection : Theoretical Computer Science Spring School: Machine Learning / Ecole de Printemps d'Informatique Théorique : Apprentissage Automatique
In this tutorial I will discuss recent advances in theory of multi-armed bandits and reinforcement learning, in particular the upper confidence bound (UCB) and Thompson Sampling (TS) techniques for algorithm design and analysis.
