| bibtype |
J -
Journal Article
|
| ARLID |
0447119 |
| utime |
20240103210535.8 |
| mtime |
20150910235959.9 |
| WOS |
000363348400013 |
| SCOPUS |
84943770986 |
| DOI |
10.1016/j.ins.2015.07.038 |
| title
(primary) (eng) |
Recursive estimation of high-order Markov chains: Approximation by finite mixtures |
| specification |
| page_count |
14 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0256752 |
| ISSN |
0020-0255 |
| title
|
Information Sciences |
| volume_id |
326 |
| volume |
1 (2016) |
| page_num |
188-201 |
| publisher |
|
|
| keyword |
Markov chain |
| keyword |
Approximate parameter estimation |
| keyword |
Bayesian recursive estimation |
| keyword |
Adaptive systems |
| keyword |
Kullback–Leibler divergence |
| keyword |
Forgetting |
| author
(primary) |
| ARLID |
cav_un_auth*0101124 |
| name1 |
Kárný |
| name2 |
Miroslav |
| full_dept (cz) |
Adaptivní systémy |
| full_dept (eng) |
Department of Adaptive Systems |
| department (cz) |
AS |
| department (eng) |
AS |
| institution |
UTIA-B |
| full_dept |
Department of Adaptive Systems |
| share |
100 |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| cas_special |
| project |
| project_id |
GA13-13502S |
| agency |
GA ČR |
| ARLID |
cav_un_auth*0292725 |
|
| abstract
(eng) |
A high-order Markov chain is a universal model of stochastic relations between discrete-valued variables. The exact estimation of its transition probabilities suffers from the curse of dimensionality. It requires an excessive amount of informative observations as well as an extreme memory for storing the corresponding sufficient statistic. The paper bypasses this problem by considering a rich subset of Markov-chain models, namely, mixtures of low dimensional Markov chains, possibly with external variables. It uses Bayesian approximate estimation suitable for a subsequent decision making under uncertainty. The proposed recursive (sequential, one-pass) estimator updates a product of Dirichlet probability densities (pds) used as an approximate posterior pd, projects the result back to this class of pds and applies an improved data-dependent stabilised forgetting, which counteracts the dangerous accumulation of approximation errors. |
| reportyear |
2016 |
| RIV |
BC |
| num_of_auth |
1 |
| mrcbC52 |
4 A hod 4ah 20231122141128.6 |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0249079 |
| mrcbC64 |
1 Department of Adaptive Systems UTIA-B 10200 COMPUTER SCIENCE, INFORMATION SYSTEMS |
| confidential |
S |
| mrcbC86 |
2 Article Computer Science Information Systems |
| mrcbT16-e |
COMPUTERSCIENCEINFORMATIONSYSTEMS |
| mrcbT16-j |
1.09 |
| mrcbT16-s |
1.781 |
| mrcbT16-4 |
Q1 |
| mrcbT16-B |
80.37 |
| mrcbT16-D |
Q1 |
| mrcbT16-E |
Q1 |
| arlyear |
2016 |
| mrcbTft |
\nSoubory v repozitáři: karny-0447119.pdf |
| mrcbU14 |
84943770986 SCOPUS |
| mrcbU34 |
000363348400013 WOS |
| mrcbU63 |
cav_un_epca*0256752 Information Sciences 0020-0255 1872-6291 Roč. 326 č. 1 2016 188 201 Elsevier |
|