arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1203.3472cs.LGstat.ML
收藏

来自Kernel Herding的超级样本

Super-Samples from Kernel Herding

Department of Computer Science(计算机科学系);Yahoo! Research(雅虎研究院);University of California, Irvine(加州大学欧文分校)

Yutian Chen, Max Welling, Alex Smola

摘要:

利用核技巧将羊群算法推广到连续空间。由此产生的“内核羊群”算法是一个无限内存的确定性过程,学习近似PDF与样本的集合。我们表明,核羊群减少的期望在希尔伯特空间中的函数的错误率O(1/T),这是比通常的O(1/pT)iid随机样本快得多。我们说明内核羊群近似贝叶斯预测分布。

英文摘要:

We extend the herding algorithm to continuous spaces by using the kernel trick. The resulting "kernel herding" algorithm is an infinite memory deterministic process that learns to approximate a PDF with a collection of samples. We show that kernel herding decreases the error of expectations of functions in the Hilbert space at a rate O(1/T) which is much faster than the usual O(1/pT) for iid random samples. We illustrate kernel herding by approximating Bayesian predictive distributions.

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。

↑