Abstract:Experimental design has emerged as a powerful approach for improving the sample efficiency of A/B testing, yet existing designs rely critically on correctly specified models. We study robust sequential experimental design under model misspecification and develop a unified framework that covers both contextual bandit and dynamic settings. Theoretically, we prove that our design bounds the worst-case mean squared error of the estimated treatment effect. Empirically, we demonstrate the effectiveness of the proposed approach using synthetic and real-world datasets from a leading technology company.
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.12899 [stat.ML] |
| (or arXiv:2605.12899v1 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2605.12899 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qianglin Wen [view email]
[v1]
Wed, 13 May 2026 02:24:57 UTC (296 KB)