arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.00528cs.LGcs.ITcs.MAmath.IT
收藏

ICQ:一种用于比特受限信道下最优臂识别的量化方案

ICQ: A Quantization Scheme for Best-Arm Identification Over Bit-Constrained Channels

IIT Bombay(印度理工学院孟买分校);EPFL(洛桑联邦理工学院)

Fathima Zarin Faizal, Adway Girish, Manjesh Kumar Hanawal, Nikhil Karamchandani

AI总结:

针对分布式多臂老虎机比特受限通信下的最优臂识别问题,提出ICQ量化方案,适配连续消除法等置信界算法,实现阶最优样本复杂度与指数级稀疏通信,经实验验证性能优于现有量化方法。

摘要:

我们研究了多臂老虎机分布式变体中的最优臂识别问题,该场景包含一个中心学习器和多个智能体。每个智能体对应老虎机的一个臂,生成服从未知分布的随机奖励。此外,每个智能体只能通过比特受限信道与学习器通信观测到的奖励。我们提出了一种名为Inflating Confidence for Quantization(ICQ,置信度膨胀量化)的新型量化方案,可应用于现有的基于置信界的学习算法,例如Successive Elimination(连续消除法)。我们分析了ICQ应用于连续消除法的性能,证明整体算法ICQ-SE具有与(未量化的)SE算法阶数最优一致的样本复杂度。此外,它仅需要学习器与智能体之间指数级稀疏的通信频率,因此成功识别最优臂所需的比特数远少于现有量化方案。我们通过数值实验验证了ICQ相较于其他量化方法的性能提升。

英文摘要:

We study the problem of best-arm identification in a distributed variant of the multi-armed bandit setting, with a central learner and multiple agents. Each agent is associated with an arm of the bandit, generating stochastic rewards following an unknown distribution. Further, each agent can communicate the observed rewards with the learner over a bit-constrained channel. We propose a novel quantization scheme called Inflating Confidence for Quantization (ICQ) that can be applied to existing confidence-bound based learning algorithms such as Successive Elimination. We analyze the performance of ICQ applied to Successive Elimination and show that the overall algorithm, named ICQ-SE, has the order-optimal sample complexity as that of the (unquantized) SE algorithm. Moreover, it requires only an exponentially sparse frequency of communication between the learner and the agents, thus requiring considerably fewer bits than existing quantization schemes to successfully identify the best arm. We validate the performance improvement offered by ICQ with other quantization methods through numerical experiments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑