arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1411.0169cs.LGcs.DSmath.STstat.TH
收藏

基于变宽度直方图的近线性时间密度估计

Near-Optimal Density Estimation in Near-Linear Time Using Variable-Width Histograms

Microsoft Research, New England(微软新英格兰研究院);University of Edinburgh(爱丁堡大学);Columbia University(哥伦比亚大学)

Siu-On Chan, Ilias Diakonikolas, Rocco A. Servedio, Xiaorui Sun

摘要:

令$p$是$[0,1)$上的未知且任意的概率分布。考虑{ \em密度估计}问题,给出了独立同分布的学习算法.从$p$中提取,并且必须(以高概率)输出接近$p$的假设分布。本文的主要贡献是一个高效的密度估计算法学习使用可变宽度直方图,即,具有分段恒定概率密度函数的假设分布。更详细地说,对于任何$k$和$ε$,我们给出了一个算法,使$\tilde{O}(k/ε^2)$从$p$绘制,运行在$\tilde{O}(k/ε^2)$时间,并输出一个假设分布$h$,这是分段恒定的$O(k \log^2(1/ε))$件。假设$h$以高概率满足$d_{\mathrm{TV}}(p,h) \leq C \cdot \mathrm{opt}_k(p) + ε$,其中$d_{\mathrm{TV}}$表示总变异距离(统计距离),$C$是通用常数,而$\mathrm{opt}_k(p)$是$p$与任何$k$分段常数分布之间的最小总变异距离。我们的算法的样本量和运行时间是最佳的对数因子。在我们的结果中的“近似因子”$C$是固有的问题,因为我们证明了,没有算法的样本大小有界的$k$和$ε$可以实现$C<2$,无论它使用什么样的假设分布。

英文摘要:

Let $p$ be an unknown and arbitrary probability distribution over $[0,1)$. We consider the problem of {\em density estimation}, in which a learning algorithm is given i.i.d. draws from $p$ and must (with high probability) output a hypothesis distribution that is close to $p$. The main contribution of this paper is a highly efficient density estimation algorithm for learning using a variable-width histogram, i.e., a hypothesis distribution with a piecewise constant probability density function. In more detail, for any $k$ and $ε$, we give an algorithm that makes $\tilde{O}(k/ε^2)$ draws from $p$, runs in $\tilde{O}(k/ε^2)$ time, and outputs a hypothesis distribution $h$ that is piecewise constant with $O(k \log^2(1/ε))$ pieces. With high probability the hypothesis $h$ satisfies $d_{\mathrm{TV}}(p,h) \leq C \cdot \mathrm{opt}_k(p) + ε$, where $d_{\mathrm{TV}}$ denotes the total variation distance (statistical distance), $C$ is a universal constant, and $\mathrm{opt}_k(p)$ is the smallest total variation distance between $p$ and any $k$-piecewise constant distribution. The sample size and running time of our algorithm are optimal up to logarithmic factors. The "approximation factor" $C$ in our result is inherent in the problem, as we prove that no algorithm with sample size bounded in terms of $k$ and $ε$ can achieve $C<2$ regardless of what kind of hypothesis distribution it uses.

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。

↑