Dynamic Selection in Algorithmic Decision-making
Jin Li, Ye Luo, Xiaowei Zhang

TL;DR
This paper addresses the challenge of bias in online decision algorithms caused by endogenous data, proposing an instrumental-variable method to correct bias and achieve low regret with valid statistical inference.
Contribution
It introduces a novel instrumental-variable-based algorithm for dynamic selection in online learning, correcting bias and providing theoretical guarantees.
Findings
The algorithm achieves logarithmic regret levels.
A central limit theorem for inference is established.
A new technique untangles data-action interdependence.
Abstract
This paper identifies and addresses dynamic selection problems in online learning algorithms with endogenous data. In a contextual multi-armed bandit model, a novel bias (self-fulfilling bias) arises because the endogeneity of the data influences the choices of decisions, affecting the distribution of future data to be collected and analyzed. We propose an instrumental-variable-based algorithm to correct for the bias. It obtains true parameter values and attains low (logarithmic-like) regret levels. We also prove a central limit theorem for statistical inference. To establish the theoretical properties, we develop a general technique that untangles the interdependence between data and actions.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research · Machine Learning and Algorithms · Data Stream Mining Techniques
