arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.14580cs.LGstat.ML
收藏

可复制的约束老虎机

Replicable Constrained Bandits

Politecnico di Milano(米兰理工大学)

Matteo Bollini, Gianmarco Genalti, Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi

AI总结:

本文提出了一种可复制的约束老虎机算法,通过设计满足约束条件的策略,实现了在相同环境下决策序列的可重复性,并展示了UCB-like算法在可复制性上的应用。

摘要:

算法的可复制性最近被引入,以解决机器学习中可重复实验的需求。一个可复制的在线学习算法是在相同环境中,不同执行中采取相同决策序列的概率较高的算法。我们首次研究了约束老虎机问题中的算法可复制性,其中学习者在未知的随机环境中进行T轮交互,不仅要最大化奖励,还要满足多个约束。我们的主要结果是,在约束老虎机中可以实现可复制性。具体而言,我们设计了可复制的算法,其后悔和约束违反程度在T方面与不可复制的算法相匹配。作为实现这些保证的关键步骤,我们开发了第一个适用于无约束老虎机的可复制UCB-like算法,证明了采用不确定性面前乐观原则的算法可以是可复制的,这一结果我们认为具有独立价值。

英文摘要:

Algorithmic \emph{replicability} has recently been introduced to address the need for reproducible experiments in machine learning. A \emph{replicable online learning} algorithm is one that takes the same sequence of decisions across different executions in the same environment, with high probability. We initiate the study of algorithmic replicability in \emph{constrained} MAB problems, where a learner interacts with an unknown stochastic environment for $T$ rounds, seeking not only to maximize reward but also to satisfy multiple constraints. Our main result is that replicability can be achieved in constrained MABs. Specifically, we design replicable algorithms whose regret and constraint violation match those of non-replicable ones in terms of $T$. As a key step toward these guarantees, we develop the first replicable UCB-like algorithm for \emph{unconstrained} MABs, showing that algorithms that employ the optimism in-the-face-of-uncertainty principle can be replicable, a result that we believe is of independent interest.

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。

↑