Riemannian geometry on non-parametric probability space

被引:0
|
作者
Combe-Nencka, H.
Combe, Ph.
机构
[1] CNRS Lunimy, CPT, F-13288 Marseille 09, France
[2] Univ Aix Marseille 1, F-13331 Marseille 3, France
关键词
non-parametric statistics; probability spaces; information theory; real Hilbert spaces; Riemannian infinite manifolds; geodesics flows;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The family P-lambda of absolutely continuous probabilities w.r.t. the sigma-finite measure lambda is equipped with a structure of an infinite dimensional Riemannian manifold modeled on a real Hilbert. Firstly, the relation between the Hellinger distance and the Fischer metric is analysed on the positive cone M-lambda(+) of bounded measures absolutely continuous w.r.t. lambda, appearing as a flat Riemannian manifold. Secondly, the statistical manifold P-lambda is seen as a submanifold of M-lambda(+) and Amari-Chensov alpha-connections are derived. Some alpha-self-parallel curves are explicitely exhibited.
引用
收藏
页码:459 / 473
页数:15
相关论文
共 50 条
  • [31] Non-Parametric Parametricity
    Neis, Georg
    Dreyer, Derek
    Rossberg, Andreas
    ACM SIGPLAN NOTICES, 2009, 44 (8-9) : 135 - 148
  • [32] Non-Parametric Parametricity
    Nei, Georg
    Dreyer, Derek
    Rossberg, Andreas
    ICFP'09: PROCEEDINGS OF THE 2009 ACM SIGPLAN INTERNATIONAL CONFERENCE ON FUNCTIONAL PROGRAMMING, 2009, : 135 - 148
  • [33] Non-parametric parametricity
    Neis, Georg
    Dreyer, Derek
    Rossberg, Andreas
    JOURNAL OF FUNCTIONAL PROGRAMMING, 2011, 21 : 497 - 562
  • [34] Parametric and Non-parametric Encompassing Procedures
    Bontemps, Christophe
    Florens, Jean-Pierre
    Richard, Jean-Francois
    OXFORD BULLETIN OF ECONOMICS AND STATISTICS, 2008, 70 : 751 - 780
  • [35] Non-parametric Probability Density Forecast of an Hourly Peak Load during a Month
    Bichpuriya, Yogesh K.
    Soman, S. A.
    Subramanyam, A.
    2014 POWER SYSTEMS COMPUTATION CONFERENCE (PSCC), 2014,
  • [36] Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold
    Murphy, Kieran
    Esteves, Carlos
    Jampani, Varun
    Ramalingam, Srikumar
    Makadia, Ameesh
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [37] Non-Parametric Estimation of Probability Density Functions via a Simple Interpolation Filter
    Carbone, P.
    Petri, D.
    2015 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE (I2MTC), 2015, : 1527 - 1531
  • [38] Non-parametric probability estimation for HMM-based automatic speech recognition
    Lefèvre, F
    COMPUTER SPEECH AND LANGUAGE, 2003, 17 (2-3): : 113 - 136
  • [39] NON-PARAMETRIC RECURSIVE ESTIMATES OF A PROBABILITY DENSITY-FUNCTION AND ITS DERIVATIVES
    MENON, VV
    PRASAD, B
    SINGH, RS
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1984, 9 (01) : 73 - 82
  • [40] Using multinomial and imprecise probability for non-parametric modelling of rainfall in Manizales (Colombia)
    Chivata Cardenas, Ibsen
    INGENIERIA E INVESTIGACION, 2008, 28 (02): : 22 - 29