Ergodicity of hidden Markov models

被引：13
|
作者：
Di Masi, GB
Stettner, L
机构：
[1] Polish Acad Sci, Inst Math, PL-00956 Warsaw, Poland
[2] Univ Padua, Dipartimento Matemat Pura & Applicata, I-35131 Padua, Italy
[3] CNR, ISIB, I-35131 Padua, Italy
来源：
MATHEMATICS OF CONTROL SIGNALS AND SYSTEMS | 2005年 / 17卷 / 04期
关键词：
nonlinear filtering process; invariant measures; asymptotic stability;
D O I：
10.1007/s00498-005-0153-8
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper we study ergodic properties of hidden Markov models with a generalized observation structure. In particular sufficient conditions for the existence of a unique invariant measure for the pair filter-observation are given. Furthermore, necessary and sufficient conditions for the existence of a unique invariant measure of the triple state-observation-filter are provided in terms of asymptotic stability in probability of incorrectly initialized filters. We also study the asymptotic properties of the filter and of the state estimator based on the observations as well as on the knowledge of the initial state. Their connection with minimal and maximal invariant measures is also studied.
引用
收藏
页码：269 / 296
页数：28
相关论文
共 50 条
  • [1] Ergodicity of hidden Markov models
    G.B. Di Masi
    Ł. Stettner
    Mathematics of Control, Signals and Systems, 2005, 17 : 269 - 296
  • [2] A COMPLETE SOLUTION TO BLACKWELL'S UNIQUE ERGODICITY PROBLEM FOR HIDDEN MARKOV CHAINS
    Chigansky, Pavel
    van Handel, Ramon
    ANNALS OF APPLIED PROBABILITY, 2010, 20 (06) : 2318 - 2345
  • [3] Markov property and ergodicity of the nonlinear filter
    Bhatt, AG
    Budhiraja, A
    Karandikar, RL
    SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2000, 39 (03) : 928 - 949
  • [4] Forgetting the initial distribution for Hidden Markov Models
    Douc, R.
    Fort, G.
    Moulines, E.
    Priouret, P.
    STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2009, 119 (04) : 1235 - 1256
  • [5] ON ERGODICITY OF SOME MARKOV PROCESSES
    Komorowski, Tomasz
    Peszat, Szymon
    Szarek, Tomasz
    ANNALS OF PROBABILITY, 2010, 38 (04) : 1401 - 1443
  • [6] On a Unique Ergodicity of Some Markov Processes
    Rafał Kapica
    Tomasz Szarek
    Maciej Ślȩczka
    Potential Analysis, 2012, 36 : 589 - 606
  • [7] On a Unique Ergodicity of Some Markov Processes
    Kapica, Rafal
    Szarek, Tomasz
    Sleczka, Maciej
    POTENTIAL ANALYSIS, 2012, 36 (04) : 589 - 606
  • [8] UNIFORM OBSERVABILITY OF HIDDEN MARKOV MODELS AND FILTER STABILITY FOR UNSTABLE SIGNALS
    van Handel, Ramon
    ANNALS OF APPLIED PROBABILITY, 2009, 19 (03) : 1172 - 1199
  • [9] ERGODICITY AND STABILITY OF THE CONDITIONAL DISTRIBUTIONS OF NONDEGENERATE MARKOV CHAINS
    Tong, Xin Thomson
    van Handel, Ramon
    ANNALS OF APPLIED PROBABILITY, 2012, 22 (04) : 1495 - 1540
  • [10] Approximating Markov chains and V-geometric ergodicity via weak perturbation theory
    Herve, Loic
    Ledoux, James
    STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2014, 124 (01) : 613 - 638
12345