| bibtype |
K -
Conference Paper (Czech conference)
|
| ARLID |
0041122 |
| utime |
20240111140639.2 |
| mtime |
20060920235959.9 |
| title
(primary) (eng) |
Optimality conditions for maximizers of the information divergence from an exponential family |
| specification |
| page_count |
15 s. |
| media_type |
CD-ROM |
|
| serial |
| ARLID |
cav_un_epca*0076774 |
| ISBN |
80-245-1079-0 |
| title
|
WUPES '06 Proceedings of 7th Workshop on Uncertainty Processing |
| page_num |
96-110 |
| publisher |
| place |
Prague |
| name |
University of Economics |
| year |
2006 |
|
| editor |
|
| editor |
|
|
| title
(cze) |
Optimální podmínky pro maximalizaci informační divergence exponenciální rodiny |
| keyword |
Kullback-Leibler divergence |
| keyword |
relative entropy |
| keyword |
exponential family |
| keyword |
information projection |
| keyword |
cumulant generating function |
| keyword |
log-Laplace transform |
| author
(primary) |
| ARLID |
cav_un_auth*0101161 |
| name1 |
Matúš |
| name2 |
František |
| institution |
UTIA-B |
| full_dept |
Department of Decision Making Theory |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
| source_type |
Textový soubor |
|
| COSATI |
12 |
| cas_special |
| project |
| project_id |
IAA100750603 |
| agency |
GA AV ČR |
| ARLID |
cav_un_auth*0216427 |
|
| research |
CEZ:AV0Z10750506 |
| abstract
(eng) |
The information divergence of a probability measure P from an exponential family E over a finite set is defined as infimum of the divergences of P from Q subject to Q in E. All directional derivatives of the divergence from E are explicitly found. To this end, behaviour of the conjugate of a log-Laplace transform on the boundary of its domain is analysed. The first order conditions for P to be a maximizer of the divergence from E are presented, including new ones when P is not projectable to E. |
| abstract
(cze) |
Informační divergence pravděpodobnostní míry P od exponenciální rodiny se definuje jako infimum divergencí P od Q v E. Byly spočteny směrové derivace této divergence pomocí nových výsledků o konjugaci log-Lapaceovy transformace. Byly formulovány nové nutné podmínky prvního řádu proto, aby P byla maximalizátorem této divergence |
| action |
| ARLID |
cav_un_auth*0216826 |
| name |
WUPES 2006 |
| place |
Mikulov |
| dates |
16.09.2006-20.09.2006 |
| country |
CZ |
|
| reportyear |
2007 |
| RIV |
BD |
| permalink |
http://hdl.handle.net/11104/0134694 |
| arlyear |
2006 |
| mrcbU56 |
Textový soubor |
| mrcbU63 |
cav_un_epca*0076774 WUPES '06 Proceedings of 7th Workshop on Uncertainty Processing 80-245-1079-0 96 110 Prague University of Economics 2006 |
| mrcbU67 |
Vejnarová J. 340 |
| mrcbU67 |
Kroupa T. 340 |
|