随机环境中马氏链的最小闭集

主要研究了随机环境中马氏链的最小闭集的一些性质,并就保守集C在何种情况下存在最小闭子集的开问题结合Foguel的L1-理论进行了讨论,得到了一些结果.     

Markov chains in random environments and random iterated function systems

We consider random iterated function systems giving rise to Markov chains in random (stationary) environments. Conditions ensuring unique ergodicity and a ``pure type' characterization of the limiting ``randomly invariant' probability measure are provided. We also give a dimension formula and an algorithm for simulating exact samples from the limiting probability measure.

     

Infinitely dimensional control Markov branching chains in random environments

First of all we introduce the concepts of infinitely dimensional control Markov branching chains in random environments (β-MBCRE) and prove the existence of such chains, then we introduce the concepts of conditional generating functionals and random Markov transition functions of such chains and investigate their branching property. Base on these concepts we calculate the moments of the β-MBCRE and obtain the main results of this paper such as extinction probabilities, polarization and proliferation rate. Finally we discuss the classification of β-MBCRE according to the different standards.     

On potentials of ergodic Markov chains

Two theorems on the existence of the potential of an ergodic Markov chain in an arbitrary phase space are proved.DeceasedTranslated from Ukrainskii Matematicheskii Zhurnal, Vol. 46, No. 4, pp. 446–449, April, 1994.This work was supported by the Ukrainian State Committee on Science and Technology.     

The occurrence of sequence patterns in ergodic Markov chains

The occupation measure identity is used to derive the expected waiting time for the first occurrence of a fixed finite pattern in a sequence of observations generated by an ergodic Markov chain.     

Recurrence and invariant measure of Markov chains in double-infinite random environments

The concepts of π -irreduciblity, recurrence and transience are introduced into the research field of Markov chains in random environments. That a π -irreducible chain must be either recurrent or transient is proved, a criterion is shown for recurrent Markov chains in double-infinite random environments, the existence of invariant measure of π -irreducible chains in double-infinite environments is discussed, and then Orey’s open-questions are partially answered.     

随机环境中马氏链状态的常返性与暂留性

给出了随机环境中马氏链状态必然是弱常返或强暂留的几个充分条件,引入了状态周期的概念,得到类似于经典马氏链状态周期的几个性质.引入了随机环境中马氏链状态的几个数字特征,给出了随机环境中马氏链状态是弱常返与强常返等价的充分条件,利用这一条件可以说明相关文献所出现的错误结论.     

Learning from uniformly ergodic Markov chains

Evaluation for generalization performance of learning algorithms has been the main thread of machine learning theoretical research. The previous bounds describing the generalization performance of the empirical risk minimization (ERM) algorithm are usually established based on independent and identically distributed (i.i.d.) samples. In this paper we go far beyond this classical framework by establishing the generalization bounds of the ERM algorithm with uniformly ergodic Markov chain (u.e.M.c.) samples. We prove the bounds on the rate of uniform convergence/relative uniform convergence of the ERM algorithm with u.e.M.c. samples, and show that the ERM algorithm with u.e.M.c. samples is consistent. The established theory underlies application of ERM type of learning algorithms.     

随机环境中马氏链状态的各种常返性与暂留性

考虑到随机环境中马氏链的状态在受到环境因素各种条件的影响下,引入了随机环境中马氏链状态的各种常返性与暂留性概念,讨论了这些常返性与暂留性的相互关系,从而说明随机环境中马氏链状态的常返性与暂留性和经典马氏链状态的常返性与暂留性有着显著的区别.