Similarity-Based Pattern Recognition
Similarity-Based Pattern Recognition
复制标题
基于相似性的模式识别
DOI：
10.1007/978-3-642-39140-8_10
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Martínez-Rego D
中科院分区：
文献类型：
--
作者：
Martínez-Rego D
多任务平均处理联合估计一组分布的均值的问题。它起源于五十年代，当时人们发现，利用相关分布中的数据可以比独立地从每个分布中学习获得更优异的性能。斯坦因悖论表明，在平均平方误差意义上，最好使用从所有高斯随机变量中采样的数据来估计它们的均值。这种现象在很大程度上被忽视了，最近又在多任务学习领域再次出现。在本文中，我们将多任务平均的最新结果扩展到当时维度的情况，并提出了一种从数据中检测哪些任务/分布应被视为相关的方法。我们的实验结果表明，所提出的方法与现有技术相比具有优势。
Multi-task averaging deals with the problem of estimating the means of a set of distributions jointly. It has its roots in the fifties when it was observed that leveraging data from related distributions can yield superior performance over learning from each distribution independently. Stein’s paradox showed that, in an average square error sense, it is better to estimate the means ofTGaussian random variables using data sampled from all of them. This phenomenon has been largely disregarded and has recently emerged again in the field of multi-task learning. In this paper, we extend recent results for multi-task averaging to then-dimensional case and propose a method to detect from data which tasks/distributions should be considered as related. Our experimental results indicate that the proposed method compares favorably to the state of the art.