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 2211.01743cs.LGcs.ITmath.ITmath.STstat.MLstat.TH
收藏

超越最佳:估计无限武装土匪中的分布泛函

Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits

Stanford University(斯坦福大学);Massachusetts Institute of Technology(麻省理工学院);University of California, Berkeley(加州大学伯克利分校)

Yifei Wang, Tavor Baharav, Yanjun Han, Jiantao Jiao, David Tse

摘要:

在无限臂强盗问题中,每个臂的平均奖励从未知分布中采样,并且每个臂可以进一步采样以获得该臂的平均奖励的噪声估计。估计平均奖励分布的最大值。我们认为一般类的分布泛函超出了最大值,并提出了统一的Meta算法离线和在线设置,实现最佳的样本复杂性。我们表明,在线估计,学习者可以顺序选择是否采样一个新的或现有的手臂,提供了没有优势的离线设置估计的平均功能,但显着降低了其他功能,如中位数,最大值和修剪的平均样本的复杂性。匹配下界利用几个不同的Wasserstein距离。对于中值估计的特殊情况下,我们确定了一个奇怪的阈值的现象,高斯卷积之间的不变性相对于噪声水平,这可能是独立的利益。

英文摘要:

In the infinite-armed bandit problem, each arm's average reward is sampled from an unknown distribution, and each arm can be sampled further to obtain noisy estimates of the average reward of that arm. Prior work focuses on identifying the best arm, i.e., estimating the maximum of the average reward distribution. We consider a general class of distribution functionals beyond the maximum, and propose unified meta algorithms for both the offline and online settings, achieving optimal sample complexities. We show that online estimation, where the learner can sequentially choose whether to sample a new or existing arm, offers no advantage over the offline setting for estimating the mean functional, but significantly reduces the sample complexity for other functionals such as the median, maximum, and trimmed mean. The matching lower bounds utilize several different Wasserstein distances. For the special case of median estimation, we identify a curious thresholding phenomenon on the indistinguishability between Gaussian convolutions with respect to the noise level, which may be 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。

↑