核特征空间中的匹配追踪理论Theory of Matching Pursuit in Kernel Defined Feature Spaces |
|
课程网址: | http://videolectures.net/wehys08_shawe_taylor_tmp/ |
主讲教师: | John Shawe-Taylor |
开课单位: | 伦敦大学学院 |
开课时间: | 2008-12-20 |
课程语种: | 英语 |
中文简介: | 摘要通过证明核主成分分析产生的稀疏子空间是一种样本压缩方案,分析了核主成分分析的匹配追求问题。我们证明这个界限比Shawe-Taylor等人的KPCA界限更紧,并且对于捕获数据中大部分方差所需的子空间的大小具有很高的预测性。分析了一种不符合样本压缩方案的核匹配跟踪算法。然而,我们给出了一个新的边界,将KMP算法的子空间选择作为压缩方案,从而提供了一个VC界到其未来损失的上界。最后,我们描述了相同的边界如何应用于其他匹配跟踪相关算法。 |
课程简介: | We analyse matching pursuit for kernel principal components analysis (KPCA) by proving that the sparse subspace it produces is a sample compression scheme. We show that this bound is tighter than the KPCA bound of Shawe-Taylor et al and highly predictive of the size of the subspace needed to capture most of the variance in the data. We analyse a second matching pursuit algorithm called kernel matching pursuit (KMP) which does not correspond to a sample compression scheme. However, we give a novel bound that views the choice of subspace of the KMP algorithm as a compression scheme and hence provide a VC bound to upper bound its future loss. Finally we describe how the same bound can be applied to other matching pursuit related algorithms. |
关 键 词: | 计算机科学; 机器学习; 核方法; 核主成分分析 |
课程来源: | 视频讲座网 |
最后编审: | 2021-02-04:nkq |
阅读次数: | 48 |