arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.7156math.PR
收藏

求圆上$p$ -均值的随机算法

A stochastic algorithm finding $p$-means on the circle

Marc Arnaudon, Laurent Miclo

摘要:

提出了一种随机算法,从紧黎曼流形上的概率测度$ν$和$p\in[1,\infty)$的内在$p$ -均值集中找到一些元素。它被顺序地馈送有根据$ν$分布的独立随机变量$(Y_n)_{n\in \mathbb{N}}$,这通常是$ν$的唯一可用知识。此外,该算法易于实现,因为当它在$Y_n$之一,$n\in\mathbb{N}$的方向上跳跃时,它在随机时间之间像布朗运动一样进化。它的原理是基于模拟退火和均匀化,因此温度和近似方案必须调整(如果$ν$不允许霍尔德密度,则加上正则化方案)。收敛性分析仅限于状态空间为圆的情况。在其原则上,证明依赖于调查的时间不均匀的$\mathbb{L}^2$功能和相应的频谱间隙估计由于霍利,Kusuoka和Stroock的演变。但这需要对未知的瞬时不变测度与某些方便的Gibbs测度之间的差异进行新的估计。

英文摘要:

A stochastic algorithm is proposed, finding some elements from the set of intrinsic $p$-mean(s) associated to a probability measure $ν$ on a compact Riemannian manifold and to $p\in[1,\infty)$. It is fed sequentially with independent random variables $(Y_n)_{n\in \mathbb{N}}$ distributed according to $ν$, which is often the only available knowledge of $ν$. Furthermore, the algorithm is easy to implement, because it evolves like a Brownian motion between the random times when it jumps in direction of one of the $Y_n$, $n\in\mathbb{N}$. Its principle is based on simulated annealing and homogenization, so that temperature and approximations schemes must be tuned up (plus a regularizing scheme if $ν$ does not admit a Hölderian density). The analysis of the convergence is restricted to the case where the state space is a circle. In its principle, the proof relies on the investigation of the evolution of a time-inhomogeneous $\mathbb{L}^2$ functional and on the corresponding spectral gap estimates due to Holley, Kusuoka and Stroock. But it requires new estimates on the discrepancies between the unknown instantaneous invariant measures and some convenient Gibbs measures.

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。

↑