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 2301.09573math.STcs.LGstat.MEstat.MLstat.TH
收藏

Huber稳健置信序列

Huber-Robust Confidence Sequences

Carnegie Mellon University(卡内基梅隆大学)

Hongjian Wang, Aaditya Ramdas

摘要:

置信序列是可以顺序跟踪的置信区间,并且在任意数据相关的停时有效。本文给出了一个未知分布的单变量均值的置信序列,已知$p$ -th中心矩的上界($p$ > 1),但允许(最多)任意分布腐败的$ε$分数,如在Huber的污染模型。我们这样做,通过设计新的强大的指数上鞅,并表明,由此产生的置信序列达到最佳的宽度在非序列设置。也许令人惊讶的是,我们的顺序结果和下界之间的恒定裕度甚至比基于修剪均值的固定时间稳健置信区间还要小。由于置信序列是A/B/n测试和强盗中使用的常用工具,这些结果为序列实验打开了大门,这种实验对离群值和对抗性腐败具有鲁棒性。

英文摘要:

Confidence sequences are confidence intervals that can be sequentially tracked, and are valid at arbitrary data-dependent stopping times. This paper presents confidence sequences for a univariate mean of an unknown distribution with a known upper bound on the $p$-th central moment ($p$ > 1), but allowing for (at most) $ε$ fraction of arbitrary distribution corruption, as in Huber's contamination model. We do this by designing new robust exponential supermartingales, and show that the resulting confidence sequences attain the optimal width achieved in the nonsequential setting. Perhaps surprisingly, the constant margin between our sequential result and the lower bound is smaller than even fixed-time robust confidence intervals based on the trimmed mean, for example. Since confidence sequences are a common tool used within A/B/n testing and bandits, these results open the door to sequential experimentation that is robust to outliers and adversarial corruptions.

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。

↑