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

arXiv: https://arxiv.org/abs/2402.10592 · HTML: https://mlsanity.com/paper/2402.10592/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 60 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [Optimal Best Arm Identification with Fixed Confidence](https://mlsanity.com/paper/1602.04589/) (2016)
- [Improving the Expected Improvement Algorithm](https://mlsanity.com/paper/1705.10033/) (2017)
- [Top Two Algorithms Revisited](https://mlsanity.com/paper/2206.05979/) (2022)
- [On the Existence of a Complexity in Fixed Budget Bandit Identification](https://mlsanity.com/paper/2303.09468/) (2023)
- [Clip-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments](https://mlsanity.com/paper/2305.17187/) (2023)
- [Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling](https://mlsanity.com/paper/2109.08229/) (2021)
- [Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits](https://mlsanity.com/paper/2110.08627/) (2021)
- [Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation](https://mlsanity.com/paper/2202.09036/) (2022)
- [Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning](https://mlsanity.com/paper/2211.12004/) (2022)
- [Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization](https://mlsanity.com/paper/2307.02108/) (2023)
- [Dual-Directed Algorithm Design for Efficient Pure Exploration](https://mlsanity.com/paper/2310.19319/) (2023)
- [Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization](https://mlsanity.com/paper/2112.08507/) (2021)

## Built on by (most cited first, 12 of 12)

- [Best Arm Identification with Minimal Regret](https://mlsanity.com/paper/2409.18909/) (2024)
- [Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions](https://mlsanity.com/paper/2601.15353/) (2026)
- [Logging Policy Design for Off-Policy Evaluation](https://mlsanity.com/paper/2605.15108/) (2026)
- [Admissibility of Completely Randomized Trials: A Large-Deviation Approach](https://mlsanity.com/paper/2506.05329/) (2025)
- [Pure Exploration via Frank-Wolfe Self-Play](https://mlsanity.com/paper/2509.19901/) (2025)
- [Deceptive Exploration in Multi-armed Bandits](https://mlsanity.com/paper/2510.08794/) (2025)
- [On Pareto Optimality for Parametric Choice Bandits](https://mlsanity.com/paper/2501.19277/) (2025)
- [An Algorithm for Fixed Budget Best Arm Identification with Combinatorial Exploration](https://mlsanity.com/paper/2502.01429/) (2025)
- [On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits](https://mlsanity.com/paper/2605.25789/) (2026)
- [Ranking-and-Selection with Multiple Correct Answers and Non-Answerable Estimates](https://mlsanity.com/paper/2606.21889/) (2026)
- [Experimentation and Commitment under Reward Shifts](https://mlsanity.com/paper/2607.23432/) (2026)
- [Optimal Sequential Annotations for Off-Policy Evaluation](https://mlsanity.com/paper/2609.26707/) (2026)

## Abstract (arXiv)

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.