Simple Bounds for the Convergence of Empirical and Occupation Measures in 1-Wasserstein Distance
Abstract
We study the problem of non-asymptotic deviations between a reference measure and its empirical version, in the 1-Wasserstein metric, under the standing assumption that the reference measure satisfies a transport-entropy inequality. We extend some results of F. Bolley, A. Guillin and C. Villani with simple proofs. Our methods are based on concentration inequalities and extend to the general setting of measures on a Polish space. Deviation bounds for the occupation measure of a contracting Markov chain in 1-Wasserstein distance are also given. Throughout the text, several examples are worked out, including the cases of Gaussian measures on separable Banach spaces, and laws of diffusion processes.
Full Text: Download PDF | View PDF online (requires PDF plugin)
Pages: 2296-2333
Publication Date: November 15, 2011
DOI: 10.1214/EJP.v16-958
References
- Ajtai, M.; KomlÃs, J.; Tusn·dy, G. On optimal matchings. Combinatorica 4 (1984), no. 4, 259--264. 0779885
- Baldi, P.; Ben Arous, G.; Kerkyacharian, G. Large deviations and the Strassen theorem in H?lder norm. Stochastic Process. Appl. 42 (1992), no. 1, 171--180. 1172514
- Barthe, F.; Bordenave, C. Combinatorial optimization over two random point sets. Arxiv preprint arXiv:1103.2734, 2011.
- Bobkov, S.; Ledoux, M. PoincarÃ's inequalities and Talagrand's concentration phenomenon for the exponential distribution. Probab. Theory Related Fields 107 (1997), no. 3, 383--400. 1440138
- Bobkov, S. G.; G?tze, F. Exponential integrability and transportation cost related to logarithmic Sobolev inequalities. J. Funct. Anal. 163 (1999), no. 1, 1--28. 1682772
- Boissard, E.; Le Gouic, T. On the mean speed of convergence of empirical and occupation measures in Wasserstein distance. Arxiv preprint arXiv:1105.5263, 2011.
- Bolley, F. Quantitative concentration inequalities on sample path space for mean field interaction. ESAIM Probab. Stat. 14 (2010), 192--209. 2741965
- Bolley, F.; Guillin, A.; Villani, C. Quantitative concentration inequalities for empirical measures on non-compact spaces. Probab. Theory Related Fields 137 (2007), no. 3-4, 541--593. 2280433
- Bolley, F.; Villani, C. Weighted Csisz·r-Kullback-Pinsker inequalities and applications to transportation inequalities. Ann. Fac. Sci. Toulouse Math. (6) 14 (2005), no. 3, 331--352. 2172583
- del Barrio, E.; GinÃ, E.; Matr·n, C. Central limit theorems for the Wasserstein distance between the empirical and the true distributions. Ann. Probab. 27 (1999), no. 2, 1009--1071. 1698999
- Dembo, A.; Zeitouni, O. Large deviations techniques and applications. Jones and Bartlett Publishers, Boston, MA, 1993. 1202429
- Dereich, S.; Fehringer, F.; Matoussi, A.; Scheutzow, M. On the link between small ball probabilities and the quantization problem for Gaussian measures on Banach spaces. J. Theoret. Probab. 16 (2003), no. 1, 249--265. 1956830
- Dobric, V.; Yukich, J. E. Asymptotics for transportation cost in high dimensions. J. Theoret. Probab. 8 (1995), no. 1, 97--118. 1308672
- Dudley, R. M. The speed of mean Glivenko-Cantelli convergence. Ann. Math. Statist. 40 1968 40--50. 0236977
- Fehringer, F. Kodierung von Gaussmassen. Ph.D. thesis, 2001.
- Gozlan, N.; LÃonard, C. A large deviation approach to some transportation cost inequalities. Probab. Theory Related Fields 139 (2007), no. 1-2, 235--283. 2322697
- Gozlan, N.; LÃonard, C. Transport inequalities. A survey. Markov Processes and Related Fields 16 (2010) 635-736, 2010.
- Graf, S.; Luschgy, H.; PagÃs, G. Functional quantization and small ball probabilities for Gaussian processes. J. Theoret. Probab. 16 (2003), no. 4, 1047--1062 (2004). 2033197
- Djellout, H.; Guillin, A.; Wu, L. Transportation cost-information inequalities and applications to random dynamical systems and diffusions. Ann. Probab. 32 (2004), no. 3B, 2702--2732. 2078555
- Joulin, A.; Ollivier, Y. Curvature, concentration and error estimates for Markov chain Monte Carlo. Ann. Probab. 38 (2010), no. 6, 2418--2442.2683634
- Kuelbs, J.; Li, W. V. Metric entropy and the small ball problem for Gaussian measures. J. Funct. Anal. 116 (1993), no. 1, 133--157. 1237989
- Ledoux, M. Isoperimetry and Gaussian analysis. Lectures on probability theory and statistics (Saint-Flour, 1994) , 165--294, Lecture Notes in Math., 1648, Springer, Berlin, 1996. 1600888
- Ledoux, M. The concentration of measure phenomenon. Mathematical Surveys and Monographs, 89. American Mathematical Society, Providence, RI, 2001. 1849347
- Li, W. V.; Linde, W. Approximation, metric entropy and small ball estimates for Gaussian measures. Ann. Probab. 27 (1999), no. 3, 1556--1578. 1733160
- Marton, K. Bounding bar-d-distance by informational divergence: a method to prove measure concentration. Ann. Probab. 24 (1996), no. 2, 857--866. 1404531
- Massart, P. The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. Ann. Probab. 18 (1990), no. 3, 1269--1283. 1062069
- Massart, P. Concentration inequalities and model selection. Lectures from the 33rd Summer School on Probability Theory held in Saint-Flour, 2003. Lecture Notes in Mathematics, 1896. Springer, Berlin, 2007. 2319879
- Ollivier, Y. Ricci curvature of Markov chains on metric spaces. J. Funct. Anal. 256 (2009), no. 3, 810--864. 2484937
- Rao, M. M.; Ren, Z. D. Theory of Orlicz spaces. Monographs and Textbooks in Pure and Applied Mathematics, 146. Marcel Dekker, Inc., New York, 1991. 1113700
- Revuz, D.; Yor, M. Continuous martingales and Brownian motion. Third edition. Grundlehren der Mathematischen Wissenschaften, 293. Springer-Verlag, Berlin, 1999. 1725357
- Talagrand, M. Matching random samples in many dimensions. Ann. Appl. Probab. 2 (1992), no. 4, 846--856. 1189420
- van der Vaart, A. W.; Wellner, J. A. Weak convergence and empirical processes. With applications to statistics. Springer Series in Statistics. Springer-Verlag, New York, 1996. 1385671
- Varadarajan, V. S. On the convergence of sample probability distributions. Sankhya 19 1958 23--26. 0094839
- Villani, C. Optimal transport. Old and new. Grundlehren der Mathematischen Wissenschaften, 338. Springer-Verlag, Berlin, 2009. 2459454
- Wang, R.; Wang, X.; Wu, L. Sanov's theorem in the Wasserstein distance: a necessary and sufficient condition. Statist. Probab. Lett. 80 (2010), no. 5-6, 505--512. 2593592

This work is licensed under a Creative Commons Attribution 3.0 License.