On the Foundations of Interactive Decision Making

The talk is jointly organized by the Theory of Machine Learning Lab  and the EPFL AI Center.

For on-site logistics, please use the following form to register (with your EPFL email address): Here. 


Speaker: Professor Alexander Rakhlin

Title
On the Foundations of Interactive Decision Making

Abstract
Machine learning methods are increasingly deployed in interactive environments, ranging from dynamic treatment strategies in medicine to fine-tuning of LLMs using reinforcement learning. In these settings, the learning agent interacts with the environment to collect data and necessarily faces an exploration-exploitation dilemma. We present a general framework for interactive decision making that subsumes multi-armed bandits, contextual bandits, structured bandits, and reinforcement learning. We focus on both the statistical aspect of learning---aiming to develop a tight characterization of sample complexity in terms of properties of the class of models---and on the basic algorithmic primitives.


Bio
Alexander Rakhlin is a Professor in the Department of Brain and Cognitive Sciences and the Statistics and Data Science Center at MIT. His research interests lie at the interface of Machine Learning and Statistics, with a focus on online prediction, decision-making, and the theoretical underpinnings of modern learning systems.

Recording of the talk : yes