EconBase
← All papers

Optimizing Adaptive Experiments: A Unified Approach to Regret Minimization and Best-Arm Identification

Chao Qin, Daniel Russo

arXiv 16 Feb 2024 · Machine Learning · 3 citations (OpenAlex)

arXiv:2402.10592 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Practitioners conducting adaptive experiments often encounter two competing priorities: maximizing total welfare (or `reward') through effective treatment assignment and swiftly concluding experiments to implement population-wide treatments. Current literature addresses these priorities separately, with regret minimization studies focusing on the former and best-arm identification research on the latter. This paper bridges this divide by proposing a unified model that simultaneously accounts for within-experiment performance and post-experiment outcomes. We provide a sharp theory of optimal performance in large populations that not only unifies canonical results in the literature but also uncovers novel insights. Our theory reveals that familiar algorithms, such as the recently proposed top-two Thompson sampling algorithm, can optimize a broad class of objectives if a single scalar parameter is appropriately adjusted. In addition, we demonstrate that substantial reductions in experiment duration can often be achieved with minimal impact on both within-experiment and post-experiment regret.

Citation extraction

72
references
197
in-text mentions
72
distinct cited
8
self-citations
15,506
main-text words

appendix boundary found by appendix_command · 38% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Tze Leung Lai and Herbert Robbins (1985) Asymptotically efficient adaptive allocation rules1.000166100%
2Daniel Russo (2016) Simple bayesian algorithms for best arm identification self1.00054100%
3Daniel Russo (2020) Simple bayesian algorithms for best-arm identification self0.95014686%
4Herman Chernoff (1959) Sequential design of experiments0.9416583%
5Hock Peng Chan and Tze Leung Lai (2006) Sequential generalized likelihood ratios and adaptive treatment allocation for optimal sequential selection0.87452100%
6Emilie Kaufmann, Olivier Cappé, and Aurélien Garivier (2016) On the complexity of best-arm identification in multi-armed bandit models0.84333100%
7Peter Glynn and Sandeep Juneja (2004) A large deviations perspective on ordinal optimization0.81142100%
8Tor Lattimore and Csaba Szepesvári (2020) Bandit algorithms0.7946550%
9Chao Qin, Diego Klabjan, and Daniel Russo (2017) Improving the expected improvement algorithm self0.7375340%
10Aurélien Garivier and Emilie Kaufmann (2016) Optimal best arm identification with fixed confidence0.716301037%

Showing the top 10 of 72 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Bandit Algorithms for Policy Learning: Methods, Implementation, and Welfare-performance0.40511
2Admissibility of Completely Randomized Trials: A Large-Deviation Approach0.40511