arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.08306cs.LGcs.AImath.OCstat.ML
收藏

基于交替最小化的样本高效线性元学习

Sample Efficient Linear Meta-Learning by Alternating Minimization

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Google Research(谷歌研究院);University of Washington(华盛顿大学)

Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh

摘要:

元学习综合并利用来自给定任务集的知识,以使用非常少的数据快速学习新任务。线性回归任务的元学习是该领域研究较多的基本问题。然而,现有的结果要么保证高度次优的估计误差,要么要求每个任务的$Ω(d)$样本(其中$d$是数据维度),从而提供了比单独学习每个任务几乎没有增益。在这项工作中,我们研究了一个简单的交替最小化方法(MLLAM),交替学习低维子空间和回归。我们发现,对于一个恒定的子空间维数MLLAM获得接近最优的估计误差,尽管只需要$Ω(\log d)$样本每个任务。然而,每个任务所需的样本数量随着任务数量的增加而增加。为了弥补这一点,在低噪声制度,我们提出了一种新的任务子集选择方案,确保相同的强大的统计保证MLLAM,即使有界的样本数量为任意大的任务,每个任务。

英文摘要:

Meta-learning synthesizes and leverages the knowledge from a given set of tasks to rapidly learn new tasks using very little data. Meta-learning of linear regression tasks, where the regressors lie in a low-dimensional subspace, is an extensively-studied fundamental problem in this domain. However, existing results either guarantee highly suboptimal estimation errors, or require $Ω(d)$ samples per task (where $d$ is the data dimensionality) thus providing little gain over separately learning each task. In this work, we study a simple alternating minimization method (MLLAM), which alternately learns the low-dimensional subspace and the regressors. We show that, for a constant subspace dimension MLLAM obtains nearly-optimal estimation error, despite requiring only $Ω(\log d)$ samples per task. However, the number of samples required per task grows logarithmically with the number of tasks. To remedy this in the low-noise regime, we propose a novel task subset selection scheme that ensures the same strong statistical guarantee as MLLAM, even with bounded number of samples per task for arbitrarily large number of tasks.

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。

↑