arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.11338cs.DS
收藏

Gibbs抽样的收敛性:坐标打了就跑混合的快速

Convergence of Gibbs Sampling: Coordinate Hit-and-Run Mixes Fast

Aditi Laddha, Santosh Vempala

摘要:

吉布斯采样器是一种对高维分布进行采样的通用方法,可以追溯到Turchin,1971年。在吉布斯采样器的每一步中,我们选择一个随机坐标,并从固定所有其他坐标的分布中重新采样该坐标。虽然它在过去半个世纪中得到广泛使用,但有效收敛的保证一直难以捉摸。我们证明了对于直径为$D$的$\mathbb{R}^{n}$中的凸体$K$,在$K$上的坐标打了就跑(CHAR)算法的混合时间在$n$和$D$中是多项式.我们还给出了一个下界的CHAR的电导,表明它是严格比打了就跑或球走在最坏的情况下。

英文摘要:

The Gibbs Sampler is a general method for sampling high-dimensional distributions, dating back to Turchin, 1971. In each step of the Gibbs Sampler, we pick a random coordinate and re-sample that coordinate from the distribution induced by fixing all other coordinates. While it has become widely used over the past half-century, guarantees of efficient convergence have been elusive. We show that for a convex body $K$ in $\mathbb{R}^{n}$ with diameter $D$, the mixing time of the Coordinate Hit-and-Run (CHAR) algorithm on $K$ is polynomial in $n$ and $D$. We also give a lower bound on the conductance of CHAR, showing that it is strictly worse than hit-and-run or the ball walk in the worst case.

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。

↑