MAB 2018
Introduction
Multi-Armed Bandits and Learning Algorithms, Erasmus University, 24-25 May 2018; Deadline 15 Feb
CALL FOR PAPERS:
Workshop on Multi-Armed Bandits and Learning Algorithms
Submission Deadline: February 15th, 2018
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. When the firm is simultaneously interested in learning and in revenue, i.e., in ‘learning while earning’, these problems are referred to as Multi-Armed Bandit (MAB) problems. These algorithms use tools and techniques ranging from inference, predictive analytics, and general learning algorithms to address the exploration-exploitation trade-off inherent to such problems.
Solving these problems is hard because it often involves addressing thorny challenges such as the curse of dimensionality, scalability, latency (in online problems), and others. Algorithms are often based on regret minimization, dynamic allocation indices, confidence bound, dynamic programming, sequential experimentation, knowledge gradient, and many others techniques. Learning algorithms and MABs have been successfully applied in online advertising, news recommendation, product recommendations (e.g., recommend the current best sellers versus learn about future best sellers), clinical trials (e.g., how to minimize patient exposure to ineffective treatments), experimental design, portfolio management, website design, and many other domains.
We are announcing the invitational workshop Multi-Armed Bandits. This workshop draws on recent advances in marketing science, operations research, machine learning, econometrics, and computer science. We encourage both algorithmic developments and applications based on novel methodological content.
The workshop will take place on May 24 and 25, 2018 in the Netherlands. This workshop is organized by the marketing department of the Rotterdam School of Management at Erasmus University, Rotterdam. This event will gather 50-70 participants who are actively working in the development and application of multi-armed bandits and learning algorithms in various disciplines. For more details please refer to the workshop website at
.
Invited authors can submit their abstracts by email (pdf file only) to MAB2018@rsm.nl. There will be no published proceedings. Submissions for the workshop are due on February 15th, 2018.
Program Committee
- John Hauser, MIT
- Nicolo Cesa-Bianchi, Milan
- Theodoros Evgenios, INSEAD
- Juanjuan Zhang, MIT
- Peter Jacko, Lancaster
- Warren Powell, Princeton
- Kanishka Misra, UC San Diego
- Shie Mannor, Technion
Workshop Co-Chairs
- Gui Liberali, RSM, Erasmus University
- Vianney Perchet, CMLA, ENS-Paris Saclay & Criteo Research