We develop a family of infinite-dimensional (non-parametric) manifolds of probability measures. The latter are defined on underlying Banach spaces, and have densities of class with respect to appropriate reference measures. The case , in which the manifolds are modelled on Fréchet spaces, is included. The manifolds admit the Fisher-Rao metric and, unusually for the non-parametric setting, Amari’s -covariant derivatives for all . By construction, they are -embedded submanifolds of particular manifolds of finite measures. The statistical manifolds are dually -embedded submanifolds of particular manifolds of finite measures. The statistical manifolds are dually (α = ±1) flat, and admit mixture and exponential representations as charts. Their curvatures with respect to the α-covariant derivatives are derived. The likelihood function associated with a finite sample is a continuous function on each of the manifolds, and the α-divergences are of class C flat, and admit mixture and exponential representations as charts. Their curvatures with respect to the -covariant derivatives are derived. The likelihood function associated with a finite sample is a continuous function on each of the manifolds, and the -divergences are of class .
Mots-clés : Fisher-Rao Metric, Banach manifold, Fréchet manifold, information geometry, non-parametric statistics.
@article{PS_2018__22__19_0, author = {Newton, Nigel J.}, title = {Manifolds of differentiable densities}, journal = {ESAIM: Probability and Statistics}, pages = {19--34}, publisher = {EDP-Sciences}, volume = {22}, year = {2018}, doi = {10.1051/ps/2018003}, mrnumber = {3872126}, zbl = {1410.46056}, language = {en}, url = {http://archive.numdam.org/articles/10.1051/ps/2018003/} }
Newton, Nigel J. Manifolds of differentiable densities. ESAIM: Probability and Statistics, Tome 22 (2018), pp. 19-34. doi : 10.1051/ps/2018003. http://archive.numdam.org/articles/10.1051/ps/2018003/
[1] Methods of Information Geometry. Vol. 191 of Translations of Mathematical Monographs. American Mathematical Society, Providence (2000). | MR | Zbl
and ,[2] Information geometry and sufficient statistics. Probab. Theory Relat. Fields 162 (2015) 327–364. | DOI | MR | Zbl
, , and ,[3] Paramerized Measure Models. Bernoulli 24 (2018) 1692–1725. | MR | Zbl
, , and ,[4] Information and Exponential Families in Statistical Theory. Wiley (1978). | MR | Zbl
,[5] Uniqueness of the Fisher-Rao metric on the space of smooth densities. Bull. Lond. Math. Soc. 48 (2016) 499–506. | DOI | MR | Zbl
, and ,[6] Dimensionality reduction for measure valued evolution equations in statistical manifolds, in Computational Information Geometry for Image and Signal Processing, edited by , and . Springer (2017) 217–265. | DOI | MR
and ,[7] Geometry of the Fisher-Rao Metric on the Space of Smooth Densities on a Compact Manifold. Preprint (2016). | arXiv | MR
and ,[8] Exponential statistical manifold. Ann. Inst. Stat. Math. 59 (2007) 27–56. | DOI | MR | Zbl
and ,[9] Statistical Decision Rules and Optimal Inference. Vol. 53 of Translations of Mathematical Monographs. American Mathematical Society, Providence (1982). | Zbl
,[10] Geometry in a Fréchet Context: A Projective Limit Approach. Vol. 428 of London Mathematical Society Lecture Note Series. Cambridge University Press (2016). | MR
, and ,[11] Exponential manifold by reproducing kernel Hilbert spaces, in Algebraic and Geometric Methods in Statistics, edited by , , and . Cambridge University Press (2009) 291–306. | MR
,[12] Connections on non-parametric statistical manifolds by Orlicz space geometry. Infin. Dimens. Anal. Quantum Probab. Relat. Top. 1 (1998) 325–347. | DOI | MR | Zbl
and ,[13] Statistical Manifolds. Vol. 10 of IMS Lecture Notes Series. Institute of Mathematical Statistics (1987).
,[14] On a differential structure for the group of diffeomorphisms. Topology 46 (1967) 263–271. | DOI | MR | Zbl
,[15] Statistics of Random Processes I – General Theory. Springer (2001). | MR
and ,[16] A q-exponential statistical Banach manifold. J. Math. Ann. Appl. 398 (2013) 466–476. | DOI | MR | Zbl
and ,[17] Information geometry formalism for the spatially homogeneous Boltzmann equation. Entropy 17 (2015) 4323–4363. | DOI | MR | Zbl
and ,[18] Quantum Probability for Probabilists. Vol. 1538 of Lecture Notes in Mathematics. Springer (1995). | Zbl
,[19] Differential Geometry and Statistics. Vol. 48 of Monographs in Statistics and Applied Probability. Chapman Hall (1993). | MR | Zbl
and ,[20] Generalised Thermostatistics. Springer, London (2011). | DOI | MR | Zbl
,[21] An infinite-dimensional statistical manifold modelled on Hilbert space. J. Funct. Anal. 263 (2012) 1661–1681. | DOI | MR | Zbl
,[22] Information geometric nonlinear filtering. Infin. Dimens. Anal. Quantum Probab. Relat. Top. 18 (2015) 1550014. | DOI | MR | Zbl
,[23] Infinite-dimensional statistical manifolds based on a balanced chart. Bernoulli 22 (2016) 711–731. | DOI | MR | Zbl
,[24] Proceedings of GSI 2013 Conference. Vol. 8085 of Lecture Notes in Computer Science. Springer, Berlin (2013). | Zbl
and ,[25] Proceedings of GSI 2015 Conference. Vol. 9389 of Lecture Notes in Computer Science. Springer, Berlin (2015). | DOI | Zbl
and ,[26] The exponential statistical manifold: mean parameters, orthogonality and space transformations. Bernoulli 5 (1999) 721–760. | DOI | MR | Zbl
and ,[27] An infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one. Ann. Stat. 23 (1995) 1543–1561. | DOI | MR | Zbl
and ,[28] Information and accuracy obtainable in the estimation of statistical parameters. Bull. Calcutta Math. Soc. 37 (1945) 81–91. | MR | Zbl
,Cité par Sources :