Workshop on Multi-Armed Bandits and Learning Algorithms

May 24-25, 2018 @ Rotterdam School of Management, Erasmus University

Firms often have to sequentially decide how to allocate a finite budget among competing actions. For example, advertisers must decide which ad to show to the next website visitor given several ad copies. Online retailers must decide which products to recommend next. Learning in such situations is not trivial because choosing one alternative improves estimates about its success probability but takes resources away from a potentially better alternative. Multi-armed bandit problems, such as these, are extremely hard to solve, but extremely general and powerful. The invitational workshop on Multi-Armed Bandits and Learning Algorithms draws on recent advances in computer science, marketing science, operations research, statistics, econometrics, and machine learning. We encourage both algorithmic developments and applications based on novel methodological content.

The workshop will gather 50-70 participants who are actively working in the development and application of multi-armed bandits and learning algorithms in various disciplines.  This workshop will provide a forum for stimulating discussions, especially across the approaches that have been evolving in computer science, management science, operations research and statistics.

The workshop will take place at Erasmus University campus in Rotterdam, The Netherlands, from May 24-25, 2018 (Thursday and Friday). A poster session will be held during lunch on Thursday.

Institutional Setting and Background

The Erasmus Centre for Optimization of Digital Experiments (e-Code), which is a joint venture of the marketing department at Rotterdam School of Management at Erasmus University, and the Erasmus Research  Institute of Management, is hosting the 2018 workshop on learning algorithms and multi-armed bandits. The idea of a workshop focused on multi-armed bandits goes back to the 2016 multi-armed bandit workshop in Lancaster (U.K.) which also aimed at gathering researchers from statistics, applied probability, computer science, management science and marketing science to discuss multi-armed bandit and adaptive learning problems.

Important Dates - Invited Sessions

  • Abstract submission for invited sessions: February 15, 2018
  • Early-bird registration deadline: March 15, 2018

Important Dates - Posters

  • Extended deadline for posters: March 30,  2018
  • Notification of acceptance of posters and funding support: April 3, 2018
  • Registration deadline for posters: April 15, 2018

Workshop Dates: May 24-25, 2018