Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits

• URL: http://arxiv.org/abs/2410.15564v1
• Date: Mon, 21 Oct 2024 01:19:23 GMT
• Title: Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits
• Authors: Brian Cho, Dominik Meier, Kyra Gan, Nathan Kallus,
• Abstract summary: Good arm identification (IGA) is a practical bandit inference objective that aims to label arms with means above a threshold as quickly as possible. We show that GA can be efficiently solved by combining a reward-maximizing sampling algorithm with a novel non-valid sequential test for labeling arm means. Our empirical results validate our approach beyond the minimax setting, reducing the expected number of samples for all stopping times by at least 50% across both synthetic and real-world settings.
• Score: 35.35226227009685
• License:
• Abstract: In multi-armed bandits, the tasks of reward maximization and pure exploration are often at odds with each other. The former focuses on exploiting arms with the highest means, while the latter may require constant exploration across all arms. In this work, we focus on good arm identification (GAI), a practical bandit inference objective that aims to label arms with means above a threshold as quickly as possible. We show that GAI can be efficiently solved by combining a reward-maximizing sampling algorithm with a novel nonparametric anytime-valid sequential test for labeling arm means. We first establish that our sequential test maintains error control under highly nonparametric assumptions and asymptotically achieves the minimax optimal e-power, a notion of power for anytime-valid tests. Next, by pairing regret-minimizing sampling schemes with our sequential test, we provide an approach that achieves minimax optimal stopping times for labeling arms with means above a threshold, under an error probability constraint. Our empirical results validate our approach beyond the minimax setting, reducing the expected number of samples for all stopping times by at least 50% across both synthetic and real-world settings.

Related papers

• Best Arm Identification with Minimal Regret [55.831935724659175]
  Best arm identification problem elegantly amalgamates regret minimization and BAI. Agent's goal is to identify the best arm with a prescribed confidence level. Double KL-UCB algorithm achieves optimality as the confidence level tends to zero.
  arXiv  Detail & Related papers  (2024-09-27T16:46:02Z)
• Optimal Multi-Fidelity Best-Arm Identification [65.23078799972188]
  In bandit best-arm identification, an algorithm is tasked with finding the arm with highest mean reward with a specified accuracy as fast as possible. We study multi-fidelity best-arm identification, in which the can choose to sample an arm at a lower fidelity (less accurate mean estimate) for a lower cost. Several methods have been proposed for tackling this problem, but their optimality remain elusive, notably due to loose lower bounds on the total cost needed to identify the best arm.
  arXiv  Detail & Related papers  (2024-06-05T08:02:40Z)
• Best Arm Identification with Fixed Budget: A Large Deviation Perspective [54.305323903582845]
  We present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms. In particular, we present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms.
  arXiv  Detail & Related papers  (2023-12-19T13:17:43Z)
• Best Arm Identification in Bandits with Limited Precision Sampling [14.011731120150124]
  We study best arm identification in a variant of the multi-armed bandit problem where the learner has limited precision in arm selection. We propose a modified tracking-based algorithm to handle non-unique optimal allocations.
  arXiv  Detail & Related papers  (2023-05-10T12:07:48Z)
• Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits [40.71199236098642]
  In the infinite-armed bandit problem, each arm's average reward is sampled from an unknown distribution. We consider a general class of distribution functionals beyond the maximum, and propose unified meta algorithms for both the offline and online settings.
  arXiv  Detail & Related papers  (2022-11-01T18:20:10Z)
• Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination [80.53485617514707]
  This paper proposes two algorithms, a gap-based algorithm and one based on the successive elimination, for best arm identification in sub-Gaussian bandits. Specifically, for the gap-based algorithm, the sample complexity is optimal up to constant factors, while for the successive elimination, it is optimal up to logarithmic factors.
  arXiv  Detail & Related papers  (2021-11-14T21:49:58Z)
• Lenient Regret for Multi-Armed Bandits [72.56064196252498]
  We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. We suggest a new, more lenient, regret criterion that ignores suboptimality gaps smaller than some $epsilon$.
  arXiv  Detail & Related papers  (2020-08-10T08:30:52Z)
• Optimal Best-arm Identification in Linear Bandits [79.3239137440876]
  We devise a simple algorithm whose sampling complexity matches known instance-specific lower bounds. Unlike existing best-arm identification strategies, our algorithm uses a stopping rule that does not depend on the number of arms.
  arXiv  Detail & Related papers  (2020-06-29T14:25:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.