Estimation Considerations in Contextual Bandits

Maria Dimakopoulou, Susan Athey and Guido W. Imbens
Additional contact information
Maria Dimakopoulou: ?
Guido W. Imbens: Stanford University

Research Papers from Stanford University, Graduate School of Business

Abstract: Although many contextual bandit algorithms have similar theoretical guarantees, the characteristics of real-world applications oftentimes result in large performance dissimilarities across algorithms. We study a consideration for the exploration vs. exploitation framework that does not arise in non-contextual bandits: the way exploration is conducted in the present may affect the bias and variance in the potential outcome model estimation in subsequent stages of learning. We show that contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We propose new contextual bandit designs, combining parametric and non-parametric statistical estimation methods with causal inference methods in order to reduce the estimation bias that results from adaptive treatment assignment. We provide empirical evidence that guides the choice among the alternatives in different scenarios, such as prejudice (non-representative user contexts) in the initial training data.

Date: 2018-03
References: Add references at CitEc
Citations: View citations in EconPapers (2)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
Working Paper: Estimation Considerations in Contextual Bandits (2018)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ecl:stabus:3644

Access Statistics for this paper

More papers in Research Papers from Stanford University, Graduate School of Business Contact information at EDIRC.
Bibliographic data for series maintained by ().