学习低维矩阵
Learning Low-Dimensional Metrics
摘要:
本文研究了度量学习的理论基础,重点讨论了在先前工作中没有完全解决的三个关键问题:1)我们考虑学习一般的低维(低秩)度量以及稀疏度量; 2)我们开发的上,下(极大极小)界的推广误差; 3)我们用特征空间的维数和底层度量的维数/秩来量化度量学习的样本复杂度; 4)我们还限制了学习度量相对于底层真实生成度量的准确性。所有的结果都涉及到度量学习问题的新的数学方法,也为序数嵌入(又名非度量多维缩放)的特殊情况提供了新的启示。
英文摘要:
This paper investigates the theoretical foundations of metric learning, focused on three key questions that are not fully addressed in prior work: 1) we consider learning general low-dimensional (low-rank) metrics as well as sparse metrics; 2) we develop upper and lower (minimax)bounds on the generalization error; 3) we quantify the sample complexity of metric learning in terms of the dimension of the feature space and the dimension/rank of the underlying metric;4) we also bound the accuracy of the learned metric relative to the underlying true generative metric. All the results involve novel mathematical approaches to the metric learning problem, and lso shed new light on the special case of ordinal embedding (aka non-metric multidimensional scaling).
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。