arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.05751cs.LGstat.ML
收藏

自适应本征维度的压缩马氏距离度量学习

Compressive Mahalanobis Metric Learning Adapts to Intrinsic Dimension

School of Computer Science University of Birmingham Birmingham, United Kingdom

Efstratios Palias, Ata Kabán

AI总结:

针对高维下马氏度量学习问题,提出用随机压缩数据在降维空间训练满秩度量的方法,给出仅依赖数据稳定维度的理论误差界,并通过数值实验验证,还扩展了Gordon定理。

摘要:

度量学习旨在在输入空间上找到合适的距离度量,以提升基于距离的学习算法的性能。在高维场景下,通过对学习到的度量施加低秩约束,它还可用于降维。本文研究马氏(Mahalanobis)度量的学习问题,未在高维数据上训练低秩度量,而是使用数据的随机压缩版本,在该降维特征空间中训练满秩度量。我们给出了马氏度量学习误差的理论保证,该误差取决于数据支撑集的稳定维度,而非环境维度。我们的界除了假设数据是从有界支撑集独立同分布(i.i.d.)采样之外,未做其他假设,且当存在良性几何结构时会自动收紧。一个重要的组成部分是Gordon定理的扩展,该扩展本身可能具有独立研究价值。我们还通过数值实验验证了研究结果。

英文摘要:

Metric learning aims at finding a suitable distance metric over the input space, to improve the performance of distance-based learning algorithms. In high-dimensional settings, it can also serve as dimensionality reduction by imposing a low-rank restriction to the learnt metric. In this paper, we consider the problem of learning a Mahalanobis metric, and instead of training a low-rank metric on high-dimensional data, we use a randomly compressed version of the data to train a full-rank metric in this reduced feature space. We give theoretical guarantees on the error for Mahalanobis metric learning, which depend on the stable dimension of the data support, but not on the ambient dimension. Our bounds make no assumptions aside from i.i.d. data sampling from a bounded support, and automatically tighten when benign geometrical structures are present. An important ingredient is an extension of Gordon's theorem, which may be of independent interest. We also corroborate our findings by numerical experiments.

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。

↑