从粗数据估计均值:特征化与高效算法
Mean Estimation from Coarse Data: Characterizations and Efficient Algorithms
AI总结:
本文研究了从粗数据估计高斯均值的问题,解决了在凸分区下均值可识别性和计算高效估计的两个核心问题。
摘要:
粗数据出现在学习者只能观察样本部分信息时;即一个包含样本的集合而不是其精确值。这自然通过测量舍入、传感器限制和经济系统滞后而发生。我们研究从粗数据估计高斯均值,其中每个真实样本x从d维高斯分布中抽取,但只通过包含x的集合揭示。当粗样本大致具有“低”信息时,均值无法从观测样本中唯一恢复(即问题不可识别)。Fotakis、Kalavasis、Kontonis和Tzamos [FKKT21] 的最新工作表明,当未知均值可识别且分区仅由凸集组成时,可以实现样本高效的均值估计。此外,他们证明了在非凸情况下,均值估计变得NP难。然而,两个基本问题仍然开放:(1)在凸分区下,均值何时可识别?(2)在可识别性和凸分区下,是否可以实现计算高效的估计?本文解决了这两个问题。 [...]
英文摘要:
Coarse data arise when learners observe only partial information about samples; namely, a set containing the sample rather than its exact value. This occurs naturally through measurement rounding, sensor limitations, and lag in economic systems. We study Gaussian mean estimation from coarse data, where each true sample $x$ is drawn from a $d$-dimensional Gaussian distribution with identity covariance, but is revealed only through the set of a partition containing $x$. When the coarse samples, roughly speaking, have ``low'' information, the mean cannot be uniquely recovered from observed samples (i.e., the problem is not identifiable). Recent work by Fotakis, Kalavasis, Kontonis, and Tzamos [FKKT21] established that sample-efficient mean estimation is possible when the unknown mean is identifiable and the partition consists of only convex sets. Moreover, they showed that without convexity, mean estimation becomes NP-hard. However, two fundamental questions remained open: (1) When is the mean identifiable under convex partitions? (2) Is computationally efficient estimation possible under identifiability and convex partitions? This work resolves both questions. [...]
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。