Explore-Exploit Learning @MSR-NYC

Établi : October 24, 2013

This is an umbrella project for machine learning with explore-exploit tradeoff: the trade-off between acquiring and using information. This is a mature, yet very active, research area studied in Machine Learning, Theoretical Computer Science, Operations Research, and Economics. Much of our activity focuses on «multi-armed bandits» and «contextual bandits», relatively simple and yet very powerful models for explore-exploit tradeoff.

We are located in (or heavily collaborating with) Microsoft Research New York City. Most of us are involved in Multi-World Testing: an approach & system for contextual bandit learning.

Personne

Portrait de Robert Schapire

Robert Schapire

Partner Researcher

Portrait de Paul Mineiro

Paul Mineiro

Principal Data and Applied Scientist

Portrait de Siddhartha Sen

Siddhartha Sen

Principal Researcher

Portrait de Sarah Bird

Sarah Bird

Chief Product Officer of Responsible AI @ Microsoft

Portrait de Alex Slivkins

Alex Slivkins

Senior Principal Researcher

Portrait de Miro Dudík

Miro Dudík

Sr Principal Researcher Manager

Portrait de John Langford

John Langford

Partner Researcher Manager

Portrait de Markus Cozowicz

Markus Cozowicz

Senior Research Engineer