arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.07564stat.MLcs.LGstat.CO
收藏

最小化最大均值离散的贪婪算法的性能分析

Performance analysis of greedy algorithms for minimising a Maximum Mean Discrepancy

Université Côte d’Azur(蔚蓝海岸大学);CNRS(法国国家科学研究中心)

Luc Pronzato

摘要:

我们分析了几种迭代算法的概率测度$μ$的量化的性能,基于最小化的最大平均离散(MMD)。我们的分析包括核羊群,贪婪MMD最小化和序贯贝叶斯正交(SBQ)。我们发现,有限样本大小的近似误差,测量的MMD,减少为$1/n$ SBQ和内核放牧和贪婪的MMD最小化时,使用一个合适的步长序列。SBQ的近似误差上限稍好,但其他方法明显更快,计算成本仅随所选点数线性增加。通过两个数值例子说明了这一点,其中目标测量$μ$是均匀的(空间填充设计应用),并且$μ$是高斯混合。他们认为,在论文中得出的界限过于悲观,特别是SBQ。这种悲观情绪的根源是确定的,但似乎很难反驳。

英文摘要:

We analyse the performance of several iterative algorithms for the quantisation of a probability measure $μ$, based on the minimisation of a Maximum Mean Discrepancy (MMD). Our analysis includes kernel herding, greedy MMD minimisation and Sequential Bayesian Quadrature (SBQ). We show that the finite-sample-size approximation error, measured by the MMD, decreases as $1/n$ for SBQ and also for kernel herding and greedy MMD minimisation when using a suitable step-size sequence. The upper bound on the approximation error is slightly better for SBQ, but the other methods are significantly faster, with a computational cost that increases only linearly with the number of points selected. This is illustrated by two numerical examples, with the target measure $μ$ being uniform (a space-filling design application) and with $μ$ a Gaussian mixture. They suggest that the bounds derived in the paper are overly pessimistic, in particular for SBQ. The sources of this pessimism are identified but seem difficult to counter.

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。

↑