# Means in complete manifolds: uniqueness and approximation

ESAIM: Probability and Statistics (2014)

- Volume: 18, page 185-206
- ISSN: 1292-8100

## Access Full Article

top## Abstract

top## How to cite

topArnaudon, Marc, and Miclo, Laurent. "Means in complete manifolds: uniqueness and approximation." ESAIM: Probability and Statistics 18 (2014): 185-206. <http://eudml.org/doc/273639>.

@article{Arnaudon2014,

abstract = {Let M be a complete Riemannian manifold, M ∈ ℕ and p ≥ 1. We prove that almost everywhere on x = (x1,...,xN) ∈ MN for Lebesgue measure in MN, the measure $\mu (x)=N\sum _\{k=1\}^N\{x_k\}$ μ ( x ) = 1 N ∑ k = 1 N δ x k has a uniquep–mean ep(x). As a consequence, if X = (X1,...,XN) is a MN-valued random variable with absolutely continuous law, then almost surely μ(X(ω)) has a unique p–mean. In particular if (Xn)n ≥ 1 is an independent sample of an absolutely continuous law in M, then the process ep,n(ω) = ep(X1(ω),...,Xn(ω)) is well-defined. Assume M is compact and consider a probability measure ν in M. Using partial simulated annealing, we define a continuous semimartingale which converges in probability to the set of minimizers of the integral of distance at power p with respect to ν. When the set is a singleton, it converges to the p–mean.},

author = {Arnaudon, Marc, Miclo, Laurent},

journal = {ESAIM: Probability and Statistics},

keywords = {stochastic algorithms; diffusion processes; simulated annealing; homogenization; probability measures on compact riemannian manifolds; intrinsic p-means; instantaneous invariant measures; Gibbs measures; spectral gap at small temperature; probability measures on compact Riemannian manifolds; intrinsic $p$-means},

language = {eng},

pages = {185-206},

publisher = {EDP-Sciences},

title = {Means in complete manifolds: uniqueness and approximation},

url = {http://eudml.org/doc/273639},

volume = {18},

year = {2014},

}

TY - JOUR

AU - Arnaudon, Marc

AU - Miclo, Laurent

TI - Means in complete manifolds: uniqueness and approximation

JO - ESAIM: Probability and Statistics

PY - 2014

PB - EDP-Sciences

VL - 18

SP - 185

EP - 206

AB - Let M be a complete Riemannian manifold, M ∈ ℕ and p ≥ 1. We prove that almost everywhere on x = (x1,...,xN) ∈ MN for Lebesgue measure in MN, the measure $\mu (x)=N\sum _{k=1}^N{x_k}$ μ ( x ) = 1 N ∑ k = 1 N δ x k has a uniquep–mean ep(x). As a consequence, if X = (X1,...,XN) is a MN-valued random variable with absolutely continuous law, then almost surely μ(X(ω)) has a unique p–mean. In particular if (Xn)n ≥ 1 is an independent sample of an absolutely continuous law in M, then the process ep,n(ω) = ep(X1(ω),...,Xn(ω)) is well-defined. Assume M is compact and consider a probability measure ν in M. Using partial simulated annealing, we define a continuous semimartingale which converges in probability to the set of minimizers of the integral of distance at power p with respect to ν. When the set is a singleton, it converges to the p–mean.

LA - eng

KW - stochastic algorithms; diffusion processes; simulated annealing; homogenization; probability measures on compact riemannian manifolds; intrinsic p-means; instantaneous invariant measures; Gibbs measures; spectral gap at small temperature; probability measures on compact Riemannian manifolds; intrinsic $p$-means

UR - http://eudml.org/doc/273639

ER -

## References

top- [1] B. Afsari, Riemannian Lp center of mass: existence, uniqueness, and convexity. Proc. Amer. Math. Soc. S 0002–9939 (2010) 10541-5. (electronic) Zbl1220.53040MR2736346
- [2] B. Afsari, R. Tron and R. Vidal, On the convergence of gradient descent for finding the Riemannian center of mass. arXiv:1201.0925. Zbl1285.90031MR3057324
- [3] M. Arnaudon and F. Nielsen, Medians and means in Finsler geometry. LMS J. Comput. Math.15 (2012) 23–37. Zbl1293.53025MR2891143
- [4] M. Arnaudon, C. Dombry, A. Phan and L. Yang, Stochastic algorithms for computing means of probability measures Stoch. Proc. Appl.122 (2012) 1437–1455. Zbl1262.60073MR2914758
- [5] M. Arnaudon and F. Nielsen, On computing the Riemannian 1-Center. Comput. Geom.46 (2013) 93–104. Zbl1259.65036MR2949613
- [6] M. Bădoiu and K.L. Clarkson, Smaller core-sets for balls, Proc. of the fourteenth Annual ACM-SIAM Symposium on Discrete algorithms. Soc. Industrial Appl. Math. Philadelphia, PA, USA (2003) 801–802. Zbl1092.68660MR1974995
- [7] R. Bhattacharya and V. Patrangenaru, Large sample theory of intrinsic and extrinsic sample means on manifolds (i). Ann. Statis.31 (2003) 1–29. Zbl1020.62026MR1962498
- [8] S. Bonnabel, Convergence des méthodes de gradient stochastique sur les variétés riemanniennes. In GRETSI, Bordeaux (2011).
- [9] H. Cardot, P. Cénac and P.-A. Zitt, Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm, Bernoulli. Zbl1259.62068
- [10] B. Charlier, Necessary and sufficient condition for the existence of a Fréchet mean on the circle. arXiv:1109.1986. Zbl06282490MR3126155
- [11] P.T. Fletcher, S. Venkatasubramanian and S. Joshi, The geometric median on Riemannian manifolds with application to robust atlas estimation. NeuroImage 45 (2009) S143–S152.
- [12] D. Groisser, Newton’s method, zeroes of vector fields, and the Riemannian center of mass. Adv. Appl. Math.33 (2004) 95–135. Zbl1062.53025MR2064359
- [13] D. Groisser, On the convergence of some Procrustean averaging algorithms. Stochastics77 (2005) 31–60. Zbl1079.60018MR2138772
- [14] E.P. Hsu, Estimates of derivatives of the heat kernel on a compact Riemannian manifold. Proc. Amer. Math. Soc.127 (1999) 3739–3744. Zbl0948.58025MR1618694
- [15] R. Holley, S. Kusuoka and D. Stroock, Asymptotics of the spectral gap with applications to the theory of simulated annealing. J. Funct. Anal.83 (1989) 333–347. Zbl0706.58075MR995752
- [16] R. Holley and D. Stroock, Annealing via Sobolev inequalities. Commun. Math. Phys.115 (1988) 553–569. Zbl0643.60092MR933455
- [17] T. Hotz and S. Huckemann, Intrinsic mean on the circle: Uniqueness, Locus and Asymptotics. arXiv:org1108:2141. Zbl1331.62269MR3297863
- [18] W.S. Kendall, Probability, convexity and harmonic maps with small image I: uniqueness and fine existence. Proc. London Math. Soc.61 (1990) 371–406. Zbl0675.58042MR1063050
- [19] H. Le, Estimation of Riemannian barycentres. LMS J. Comput. Math.7 (2004) 193–200. Zbl1054.60011MR2085875
- [20] L. Miclo, Recuit simulé sans potentiel sur une variété compacte. Stoch. and Stochastic Reports41 (1992) 23–56. Zbl0758.60033MR1275365
- [21] L. Miclo, Recuit simulé partiel, Stoch. Process. Appl.65 (1996) 281–298. Zbl0889.60073MR1425361
- [22] S.J. Sheu, Some estimates of the transition density function of a nondegenerate diffusion Markov process. Ann. Probab.19 (1991) 538–561. Zbl0738.60060MR1106275
- [23] K.T. Sturm, Probability measures on metric spaces of nonpositive curvature, Heat kernels and analysis on manifolds, graphs, and metric spaces (Paris, 2002). Contemp. Math. Amer. Math. Soc. 338 (2003) 357–390. Zbl1040.60002MR2039961
- [24] E. Weiszfeld, Sur le point pour lequel la somme des distances de n points donnés est minimum. Tohoku Math. J.43 (1937) 355–386. Zbl0017.18007
- [25] L. Yang, Riemannian median and its estimation. LMS J. Comput. Math.13 (2010) 461–479. Zbl1226.60018MR2748393
- [26] L. Yang, Some properties of Frechet medians in Riemannian manifolds. Preprint.

## NotesEmbed ?

topTo embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.