On Universally Optimal Algorithms for A/B Testing

• URL: http://arxiv.org/abs/2308.12000v4
• Date: Tue, 4 Jun 2024 12:14:46 GMT
• Title: On Universally Optimal Algorithms for A/B Testing
• Authors: Po-An Wang, Kaito Ariu, Alexandre Proutiere,
• Abstract summary: We study the problem of best-arm identification with fixed budget in multi-armed bandits with Bernoulli rewards. For the problem with two arms, also known as the A/B testing problem, we prove that there is no algorithm that performs as well as the algorithm sampling each arm equally.
• Score: 49.429419538826444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the problem of best-arm identification with fixed budget in stochastic multi-armed bandits with Bernoulli rewards. For the problem with two arms, also known as the A/B testing problem, we prove that there is no algorithm that (i) performs as well as the algorithm sampling each arm equally (referred to as the {\it uniform sampling} algorithm) in all instances, and that (ii) strictly outperforms uniform sampling on at least one instance. In short, there is no algorithm better than the uniform sampling algorithm. To establish this result, we first introduce the natural class of {\it consistent} and {\it stable} algorithms, and show that any algorithm that performs as well as the uniform sampling algorithm in all instances belongs to this class. The proof then proceeds by deriving a lower bound on the error rate satisfied by any consistent and stable algorithm, and by showing that the uniform sampling algorithm matches this lower bound. Our results provide a solution to the two open problems presented in \citep{qin2022open}. For the general problem with more than two arms, we provide a first set of results. We characterize the asymptotic error rate of the celebrated Successive Rejects (SR) algorithm \citep{audibert2010best} and show that, surprisingly, the uniform sampling algorithm outperforms the SR algorithm in some instances.

Related papers

• Online Uniform Sampling: Randomized Learning-Augmented Approximation Algorithms with Application to Digital Health [3.534690532561709]
  We study the novel problem of online uniform sampling (OUS), where the goal is to distribute a sampling budget uniformly across unknown decision times. In the OUS problem, the algorithm is given a budget $b$ and a time horizon $T$, and an adversary then chooses a value $tau* in [b,T]$, which is revealed to the algorithm online. We present the first randomized algorithm designed for this problem and subsequently extend it to incorporate learning augmentation.
  arXiv  Detail & Related papers  (2024-02-03T02:36:59Z)
• 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)
• Fixed-Budget Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit [65.268245109828]
  We first introduce the Combinatorial Successive Asign algorithm, which is the first algorithm that can identify the best action even when the size of the action class is exponentially large. We show that the upper bound of the probability of error of the CSA algorithm matches a lower bound up to a logarithmic factor in the exponent. We experimentally compare the algorithms with previous methods and show that our algorithm performs better.
  arXiv  Detail & Related papers  (2023-10-24T09:47:32Z)
• Non-Asymptotic Analysis of a UCB-based Top Two Algorithm [4.18804572788063]
  A Top Two sampling rule for bandit identification is a method which selects the next arm to sample from among two candidate arms. Our proposed UCB-based Top Two simultaneously enjoys non-asymptotic guarantees and competitive empirical performance.
  arXiv  Detail & Related papers  (2022-10-11T13:21:59Z)
• 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)
• A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation [71.31905141672529]
  We study the widely adopted ancestral sampling algorithms for auto-regressive language models. We identify three key properties that are shared among them: entropy reduction, order preservation, and slope preservation. We find that the set of sampling algorithms that satisfies these properties performs on par with the existing sampling algorithms.
  arXiv  Detail & Related papers  (2020-09-15T17:28:42Z)
• An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits [34.06611065493047]
  This paper proposes near-optimal algorithms for the pure-exploration linear bandit problem in the fixed confidence and fixed budget settings. We provide an algorithm whose sample complexity scales with the geometry of the instance and avoids an explicit union bound over the number of arms. We also propose the first algorithm for linear bandits in the the fixed budget setting.
  arXiv  Detail & Related papers  (2020-06-21T00:56:33Z)
• 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)

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.