Invariant Bayesian estimation on manifolds. (English) Zbl 1069.62004

Summary: A frequent and well-founded criticism of the maximum a posteriori (MAP) and minimum mean squared error (MMSE) estimates of a continuous parameter \(\gamma\) taking values in a differentiable manifold \(\Gamma\) is that they are not invariant to arbitrary “reparameterizations” of \(\Gamma\). This paper clarifies the issues surrounding this problem, by pointing out the difference between coordinate invariance, which is a sine qua non for a mathematically well-defined problem, and diffeomorphism invariance, which is a substantial issue, and then provides a solution.
We first show that the presence of a metric structure on \(\Gamma\) can be used to define coordinate-invariant MAP and MMSE estimates, and we argue that this is the natural way to proceed. We then discuss the choice of a metric structure on \(\Gamma\). By imposing an invariance criterion natural within a Bayesian framework, we show that this choice is essentially unique. It does not necessarily correspond to a choice of coordinates. In cases of complete prior ignorance, when Jeffreys’ prior is used, the invariant MAP estimate reduces to the maximum likelihood estimate. The invariant MAP estimate coincides with the minimum message length (MML) estimate, but no discretization or approximation is used in its derivation.


62A01 Foundations and philosophical topics in statistics
62F10 Point estimation
62F15 Bayesian inference
62C10 Bayesian problems; characterization of Bayes procedures
53-XX Differential geometry
Full Text: DOI arXiv


[1] Amari, S. (1985). Differential-Geometrical Methods in Statistics . Lecture Notes in Satist. 28 . Springer, Berlin. · Zbl 0559.62001
[2] Barndorff-Nielsen, O. E. (1987). Differential geometry and statistics: Some mathematical aspects. Indian J. Math. 29 335–350. · Zbl 0663.62013
[3] Bernardo, J. M. (1979). Reference posterior distributions for Bayesian inference (with discussion). J. Roy. Statist. Soc. Ser. B 41 113–147. · Zbl 0428.62004
[4] Choquet-Bruhat, Y., DeWitt-Morette, C. and Dillard-Bleick, M. (1977). Analysis , Manifolds and Physics . North-Holland, Amsterdam. · Zbl 0385.58001
[5] Critchley, F., Marriott, P. and Salmon, M. (1994). Preferred point geometry and the local differential geometry of the Kullback–Leibler divergence. Ann. Statist. 22 1587–1602. JSTOR: · Zbl 0821.62004 · doi:10.1214/aos/1176325644
[6] Efron, B. and Hinkley, D. V. (1978). Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher information (with discussion). Biometrika 65 457–487. · Zbl 0401.62002 · doi:10.1093/biomet/65.3.457
[7] Karcher, H. (1977). Riemannian center of mass and mollifier smoothing. Comm. Pure Appl. Math. 30 509–541. · Zbl 0354.57005 · doi:10.1002/cpa.3160300502
[8] Kass, R. E. and Vos, P. W. (1997). Geometrical Foundations of Asymptotic Inference . Wiley, New York. · Zbl 0880.62005
[9] Kass, R. E. and Wasserman, L. (1996). The selection of prior distributions by formal rules. J. Amer. Statist. Assoc. 91 1343–1370. · Zbl 0884.62007 · doi:10.2307/2291752
[10] Murray, M. K. and Rice, J. W. (1993). Differential Geometry and Statistics . Chapman and Hall, London. · Zbl 0804.53001
[11] Oliver, J. J. and Baxter, R. A. (1995). MML and Bayesianism: Similarities and differences. Technical Report 206, Dept. Computer Science, Monash Univ.
[12] Pennec, X. (1999). Probabilities and statistics on Riemannian manifolds: Basic tools for geometric measurements. In Proc. International Workshop on Nonlinear Signal and Image Processing ( NSIP 1999 ) (A. E. Cetin, L. Akarun, A. Ertuzun, M. N. Gurcan and Y. Yardimci, eds.) 1 194–198. IEEE–EURASIP.
[13] Rao, C. R. (1945). Information and accuracy attainable in the estimation of statistical parameters. Bull. Calcutta Math. Soc. 37 81–91. · Zbl 0063.06420
[14] Wallace, C. S. and Boulton, D. M. (1968). An information measure for classification. The Computer Journal 11 185–195. · Zbl 0164.46208 · doi:10.1093/comjnl/11.2.185
[15] Wallace, C. S. and Boulton, D. M. (1975). An invariant Bayes method for point estimation. Classification Soc. Bull. 3 11–34. · Zbl 0305.68072
[16] Wallace, C. S. and Freeman, P. R. (1987). Estimation and inference by compact coding. J. Roy. Statist. Soc. Ser. B 49 240–265. · Zbl 0653.62005
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.