arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.07689math.PRcs.ITmath.IT
收藏

马尔可夫链中的熵收缩:半步、全步与连续时间

Entropy Contractions in Markov Chains: Half-Step, Full-Step and Continuous-Time

Pietro Caputo, Zongchen Chen, Yuzhou Gu, Yury Polyanskiy

AI总结:

本文研究马尔可夫链的熵收缩速度,通过构造反例否定了半步、全步和连续时间收缩系数相差常数因子的猜想,证明相关标准不等式不可改进,同时改进了收缩系数界定工具并可作为相关计算教程。

摘要:

本文研究有限马尔可夫核$P$相对于Kullback-Leibler散度(熵)的收敛(混合)速度。给定一个马尔可夫核,既可以定义离散时间马尔可夫链(其$n$步转移核由矩阵幂$P^n$给出),也可以定义连续时间马尔可夫过程(其时刻$t$的转移核由$e^{t(P-\text{Id})}$给出)。$n=1$或$t=0+$时的熵收缩分别由著名的泛函不等式——强数据处理不等式(SDPI)和修正对数Sobolev不等式(MLSI)刻画。当$P=KK^*$被表示为一个核与其伴随核的乘积时,还可以考虑“半步”收缩,即$K$的SDPI,而“全步”收缩指的是$P$的SDPI。文献[DMLM03]声称这些收缩系数(半步、全步和连续时间)通常彼此相差一个常数因子以内。我们通过构造多个不同的反例否定了这一猜想及相关猜想。具体而言,我们构造了:(a) 一个连续时间马尔可夫过程,其收缩速度比对应的离散时间过程快任意程度;(b) 一个核$P$,使得$P^{m+1}$的收缩效果比$P^m$好任意程度。因此,我们的主要结论是:比较五种常见熵和方差收缩概念的四个标准不等式通常是不可改进的。\n在分析反例的过程中,我们梳理并改进了用于界定收缩系数的工具,并刻画了各泛函不等式极值解的性质。由于我们的例子涵盖Bernoulli-Laplace模型、图上随机游走以及生灭链,本文也可作为计算这类常见马尔可夫链的MLSI、SDPI及其他常数的教程。

英文摘要:

This paper considers the speed of convergence (mixing) of a finite Markov kernel $P$ with respect to the Kullback-Leibler divergence (entropy). Given a Markov kernel one defines either a discrete-time Markov chain (with the $n$-step transition kernel given by the matrix power $P^n$) or a continuous-time Markov process (with the time-$t$ transition kernel given by $e^{t(P-\mathrm{Id})}$). The contraction of entropy for $n=1$ or $t=0+$ are characterized by the famous functional inequalities, the strong data processing inequality (SDPI) and the modified log-Sobolev inequality (MLSI), respectively. When $P=KK^*$ is written as the product of a kernel and its adjoint, one could also consider the ``half-step'' contraction, which is the SDPI for $K$, while the ``full-step'' contraction refers to the SDPI for $P$. The work [DMLM03] claimed that these contraction coefficients (half-step, full-step, and continuous-time) are generally within a constant factor of each other. We disprove this and related conjectures by working out a number of different counterexamples. In particular, we construct (a) a continuous-time Markov process that contracts arbitrarily faster than its discrete-time counterpart; and (b) a kernel $P$ such that $P^{m+1}$ contracts arbitrarily better than $P^m$. Hence, our main conclusion is that the four standard inequalities comparing five common notions of entropy and variance contraction are generally not improvable. In the process of analyzing the counterexamples, we survey and sharpen the tools for bounding the contraction coefficients and characterize properties of extremizers of the respective functional inequalities. As our examples range from Bernoulli-Laplace model, random walks on graphs, to birth-death chains, the paper is also intended as a tutorial on computing MLSI, SDPI and other constants for these types of commonly occurring Markov chains.

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。

↑