Kernel matching pursuit
Kernel matching pursuit
复制标题
DOI：
10.1023/a:1013955821559
复制
发表时间：
2002-07-01
期刊：
影响因子：
7.5
通讯作者：
Bengio, Y
中科院分区：
文献类型：
--
作者：
Vincent, P;Bengio, Y
匹配追踪算法通过将函数顺序附加到最初为空的基，来学习作为基函数的加权和的函数，以在最小二乘意义上逼近目标函数。我们展示了如何将匹配追踪扩展到使用非平方误差损失函数，以及如何使用它来构建基于内核的机器学习问题解决方案，同时保持对解决方案稀疏性的控制。我们提出了该算法的一个版本，该算法对下一个基和所有先前选择的基的权重做出最佳选择。最后，给出了 boosting 算法和 RBF 训练程序的链接，以及与用于分类的 SVM 的广泛实验比较，显示了与通常稀疏得多的模型的可比结果。
Matching Pursuit algorithms learn a function that is a weighted sum of basis functions, by sequentially appending functions to an initially empty basis, to approximate a target function in the least-squares sense. We show how matching pursuit can be extended to use non-squared error loss functions, and how it can be used to build kernel-based solutions to machine learning problems, while keeping control of the sparsity of the solution. We present a version of the algorithm that makes an optimal choice of both the next basis and the weights of all the previously chosen bases. Finally, links to boosting algorithms and RBF training procedures, as well as an extensive experimental comparison with SVMs for classification are given, showing comparable results with typically much sparser models.