Presentation | 2016-03-10 Redundancy of Bayesian Code with Markov Fractal Prior Distributions Naoya Matsukami, Tsutomu Kawabata, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Bayesian code method is used as a standard in realizing a universal noiseless source code. For a memoryless source, a mixture with an absolutely continuous prior has a redundancy, which is asymptotic to the dimension of the parameter space times the half of log data length. Extending the prior to singular distribution is an emerging research area, where studies support a conjecture that the dimension can be substituted by the R$mathrm{acute{e}}$nyi information dimension of the prior. Extending our previous proof on self-similar prior, we consider the case of Markov fractal prior, and prove the conjecture. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | universal encoding / redundancy analysis / singular prior / self-similar measure / R$mathrm{acute{e}}$nyi information dimension / markov process |
Paper # | IT2015-103,ISEC2015-62,WBS2015-86 |
Date of Issue | 2016-03-03 (IT, ISEC, WBS) |
Conference Information | |
Committee | IT / ISEC / WBS |
---|---|
Conference Date | 2016/3/10(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | The University of Electro-Communications |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | joint meeting of IT, ISEC, and WBS |
Chair | Yasutada Oohama(Univ. of Electro-Comm.) / Yukiyasu Tsunoo(NEC) / Hiromasa Habuchi(Ibaraki Univ.) |
Vice Chair | Tadashi Wadayama(Nagoya Inst. of Tech.) / Masahiro Mambo(Kanazawa Univ.) / Kazuto Ogawa(NHK) / Fumiaki Maehara(Waseda Univ.) / Minoru Okada(NAIST) |
Secretary | Tadashi Wadayama(Univ. of Electro-Comm.) / Masahiro Mambo(Wakayama Univ.) / Kazuto Ogawa(AIST) / Fumiaki Maehara(Toshiba) / Minoru Okada(Univ. of Kitakyushu) |
Assistant | Takuya Kusaka(Okayama Univ.) / Tetsuya Izu(Fujitsu Lab.) / Takaaki Mizuki(Tohoku Univ.) / Noritaka Yamashita(NEC) / Yusuke Kozawa(Tokyo Univ. of Science) / Akira Nakamura(Tokyo Univ. of Science) / Ryohei Nakamura(National Defense Academy) |
Paper Information | |
Registration To | Technical Committee on Information Theory / Technical Committee on Information Security / Technical Committee on Wideband System |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Redundancy of Bayesian Code with Markov Fractal Prior Distributions |
Sub Title (in English) | |
Keyword(1) | universal encoding |
Keyword(2) | redundancy analysis |
Keyword(3) | singular prior |
Keyword(4) | self-similar measure |
Keyword(5) | R$mathrm{acute{e}}$nyi information dimension |
Keyword(6) | markov process |
1st Author's Name | Naoya Matsukami |
1st Author's Affiliation | The University of Electro-Communications(UEC) |
2nd Author's Name | Tsutomu Kawabata |
2nd Author's Affiliation | The University of Electro-Communications(UEC) |
Date | 2016-03-10 |
Paper # | IT2015-103,ISEC2015-62,WBS2015-86 |
Volume (vol) | vol.115 |
Number (no) | IT-500,ISEC-501,WBS-502 |
Page | pp.pp.13-17(IT), pp.13-17(ISEC), pp.13-17(WBS), |
#Pages | 5 |
Date of Issue | 2016-03-03 (IT, ISEC, WBS) |