Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem

• URL: http://arxiv.org/abs/2511.10619v1
• Date: Fri, 14 Nov 2025 02:00:14 GMT
• Title: Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem
• Authors: Avrim Blum, Marten Garicano, Kavya Ravichandran, Dravyansh Sharma,
• Abstract summary: A growing line of work has designed algorithms for improving bandits, albeit with somewhat pessimistic worst-case guarantees.<n>In this work, we propose two new parameterized families of bandit algorithms and bound the sample complexity of learning the near-optimal algorithm from each family using offline data.<n>We show that an appropriately chosen algorithm from this family can achieve stronger guarantees, with optimal dependence on $k$, when the arm reward curves satisfy additional properties related to the strength of concavity.
• Score: 15.511904255232814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The improving multi-armed bandits problem is a formal model for allocating effort under uncertainty, motivated by scenarios such as investing research effort into new technologies, performing clinical trials, and hyperparameter selection from learning curves. Each pull of an arm provides reward that increases monotonically with diminishing returns. A growing line of work has designed algorithms for improving bandits, albeit with somewhat pessimistic worst-case guarantees. Indeed, strong lower bounds of $Ω(k)$ and $Ω(\sqrt{k})$ multiplicative approximation factors are known for both deterministic and randomized algorithms (respectively) relative to the optimal arm, where $k$ is the number of bandit arms. In this work, we propose two new parameterized families of bandit algorithms and bound the sample complexity of learning the near-optimal algorithm from each family using offline data. The first family we define includes the optimal randomized algorithm from prior work. We show that an appropriately chosen algorithm from this family can achieve stronger guarantees, with optimal dependence on $k$, when the arm reward curves satisfy additional properties related to the strength of concavity. Our second family contains algorithms that both guarantee best-arm identification on well-behaved instances and revert to worst case guarantees on poorly-behaved instances. Taking a statistical learning perspective on the bandit rewards optimization problem, we achieve stronger data-dependent guarantees without the need for actually verifying whether the assumptions are satisfied.

Related papers

• 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.<n>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.<n>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)
• Combinatorial Stochastic-Greedy Bandit [79.1700188160944]
  We propose a novelgreedy bandit (SGB) algorithm for multi-armed bandit problems when no extra information other than the joint reward of the selected set of $n$ arms at each time $tin [T]$ is observed. SGB adopts an optimized-explore-then-commit approach and is specifically designed for scenarios with a large set of base arms.
  arXiv  Detail & Related papers  (2023-12-13T11:08:25Z)
• Best arm identification in rare events [0.43012765978447565]
  A key application of this framework is in online advertising where click rates of advertisements could be a fraction of a single percent and final conversion to sales, while highly profitable, may again be a small fraction of the click rates. Lately, algorithms for BAI problems have been developed that minimise sample complexity while providing statistical guarantees on the correct arm selection. We exploit the fact that the reward process for each arm is well approximated by a Compound Poisson process to arrive at algorithms that are faster, with a small increase in sample complexity.
  arXiv  Detail & Related papers  (2023-03-14T04:51:24Z)
• 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)
• 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)
• On Regret with Multiple Best Arms [12.315392649501101]
  We study a regret problem with the existence of multiple best/near-optimal arms in a bandit setting. Our goal is to design algorithms that can automatically adapt to the unknown hardness of the problem.
  arXiv  Detail & Related papers  (2020-06-26T04:01:46Z)
• Corralling Stochastic Bandit Algorithms [54.10645564702416]
  We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward. We show that the gap between the highest reward and other rewards depends on the gap between the highest reward and other rewards.
  arXiv  Detail & Related papers  (2020-06-16T15:33:12Z)
• Bandit algorithms to emulate human decision making using probabilistic distortions [20.422725678982726]
  We formulate two sample multi-armed bandit problems with distorted probabilities on the reward distributions. We consider the aforementioned problems in the regret minimization as well as best arm identification framework for multi-armed bandits.
  arXiv  Detail & Related papers  (2016-11-30T17:37:51Z)

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.