关于时间可逆马氏链平稳分布的逼近
On approximating the stationary distribution of time-reversible Markov chains
摘要:
通过马尔可夫链蒙特卡罗技术来近似马尔可夫链中状态的平稳概率通常是低效的。标准的随机游走方法需要$\tilde{O}(τ/π(v))$操作来近似链中状态$v$的概率$π(v)$与混合时间$τ$,并且即使最好的可用技术仍然具有复杂度$\tilde{O}(τ^{1.5}/π(v)^{0.5})$,并且由于这些复杂度与$π(v)$成反比,因此它们可以增长超过链的大小或其混合时间的任何界限。在本文中,我们表明,时间可逆的马尔可夫链,存在一个简单的随机近似算法,打破了这个“小$π(v)$障碍”。
英文摘要:
Approximating the stationary probability of a state in a Markov chain through Markov chain Monte Carlo techniques is, in general, inefficient. Standard random walk approaches require $\tilde{O}(τ/π(v))$ operations to approximate the probability $π(v)$ of a state $v$ in a chain with mixing time $τ$, and even the best available techniques still have complexity $\tilde{O}(τ^{1.5}/π(v)^{0.5})$, and since these complexities depend inversely on $π(v)$, they can grow beyond any bound in the size of the chain or in its mixing time. In this paper we show that, for time-reversible Markov chains, there exists a simple randomized approximation algorithm that breaks this "small-$π(v)$ barrier".
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。