Jump to ContentJump to Main Navigation
Show Summary Details
More options …

Dependence Modeling

Ed. by Puccetti, Giovanni

1 Issue per year

Covered by:

Open Access
See all formats and pricing
More options …

Prediction of time series by statistical learning: general losses and fast rates

Pierre Alquier / Xiaoyin Li / Olivier Wintenberger
Published Online: 2013-12-31 | DOI: https://doi.org/10.2478/demo-2013-0004


We establish rates of convergences in statistical learning for time series forecasting. Using the PAC-Bayesian approach, slow rates of convergence √ d/n for the Gibbs estimator under the absolute loss were given in a previous work [7], where n is the sample size and d the dimension of the set of predictors. Under the same weak dependence conditions, we extend this result to any convex Lipschitz loss function. We also identify a condition on the parameter space that ensures similar rates for the classical penalized ERM procedure. We apply this method for quantile forecasting of the French GDP. Under additional conditions on the loss functions (satisfied by the quadratic loss function) and for uniformly mixing processes, we prove that the Gibbs estimator actually achieves fast rates of convergence d/n. We discuss the optimality of these different rates pointing out references to lower bounds when they are available. In particular, these results bring a generalization the results of [29] on sparse regression estimation to some autoregression.

Keywords: Statistical learning theory; time series forecasting; PACBayesian bounds; weak dependence; mixing; oracle inequalities; fast rates; GDP forecasting

MSC: 62M20; 60G25; 62M10; 62P20; 65G15; 68Q32; 68T05

  • [1] A. Agarwal and J. C. Duchi, The generalization ability of online algorithms for dependent data, IEEE Trans. Inform. Theory 59 (2011), no. 1, 573–587. Google Scholar

  • [2] H. Akaike, Information theory and an extension of the maximum likelihood principle, 2nd International Symposium on Information Theory (B. N. Petrov and F. Csaki, eds.), Budapest: Akademia Kiado, 1973, pp. 267–281. Google Scholar

  • [3] P. Alquier and P. Lounici, PAC-Bayesian bounds for sparse regression estimation with exponential weights, Electron. J. Stat. 5 (2011), 127–145. CrossrefGoogle Scholar

  • [4] P. Alquier, PAC-Bayesian bounds for randomized empirical risk minimizers, Math. Methods Statist. 17 (2008), no. 4, 279–304. CrossrefGoogle Scholar

  • [5] K. B. Athreya and S. G. Pantula, Mixing properties of Harris chains and autoregressive processes, J. Appl. Probab. 23 (1986), no. 4, 880–892. MR 867185 (88c:60127) Google Scholar

  • [6] J.-Y. Audibert, Fast rates in statistical inference through aggregation, Ann. Statist. 35 (2007), no. 2, 1591–1646. Google Scholar

  • [7] P. Alquier and O. Wintenberger, Model selection for weakly dependent time series forecasting, Bernoulli 18 (2012), no. 3, 883–193. CrossrefGoogle Scholar

  • [8] G. Biau, O. Biau, and L. Rouvière, Nonparametric forecasting of the manufacturing output growth with firm-level survey data, Journal of Business Cycle Measurement and Analysis 3 (2008), 317–332. Google Scholar

  • [9] A. Belloni and V. Chernozhukov, L1-penalized quantile regression in high-dimensional sparse models, Ann. Statist. 39 (2011), no. 1, 82–130. CrossrefGoogle Scholar

  • [10] P. Brockwell and R. Davis, Time series: Theory and methods (2nd edition), Springer, 2009. Google Scholar

  • [11] E. Britton, P. Fisher, and J. Whitley, The inflation report projections: Understanding the fan chart, Bank of England Quarterly Bulletin 38 (1998), no. 1, 30–37. Google Scholar

  • [12] L. Birgé and P. Massart, Gaussian model selection, J. Eur. Math. Soc. 3 (2001), no. 3, 203–268. Google Scholar

  • [13] G. Biau and B. Patra, Sequential quantile prediction of time series, IEEE Trans. Inform. Theory 57 (2011), 1664– 1674. CrossrefGoogle Scholar

  • [14] F. Bunea, A. B. Tsybakov, and M. H. Wegkamp, Aggregation for gaussian regression, Ann. Statist. 35 (2007), no. 4, 1674–1697. CrossrefGoogle Scholar

  • [15] O. Catoni, A PAC-Bayesian approach to adaptative classification, preprint (2003). Google Scholar

  • [16] O. Catoni, Statistical learning theory and stochastic optimization, Springer Lecture Notes in Mathematics, 2004. Google Scholar

  • [17] O. Catoni, PAC-Bayesian supervised classification (the thermodynamics of statistical learning), Lecture Notes- Monograph Series, vol. 56, IMS, 2007. Google Scholar

  • [18] N. Cesa-Bianchi and G. Lugosi, Prediction, learning, and games, Cambridge University Press, New York, 2006. Google Scholar

  • [19] L. Clavel and C. Minodier, A monthly indicator of the french business climate, Documents de Travail de la DESE, 2009. Google Scholar

  • [20] M. Cornec, Constructing a conditional gdp fan chart with an application to french business survey data, 30th CIRET Conference, New York, 2010. Google Scholar

  • [21] N. V. Cuong, L. S. Tung Ho, and V. Dinh, Generalization and robustness of batched weighted average algorithm with v-geometrically ergodic markov data, Proceedings of ALT’13 (Jain S., R. Munos, F. Stephan, and T. Zeugmann, eds.), Springer, 2013, pp. 264–278. Google Scholar

  • [22] J. C. Duchi, A. Agarwal, M. Johansson, and M. I. Jordan, Ergodic mirror descent, SIAM J. Optim. 22 (2012), no. 4, 1549–1578. Google Scholar

  • [23] J. Dedecker, P. Doukhan, G. Lang, J. R. León, S. Louhichi, and C. Prieur, Weak dependence, examples and applications, Lecture Notes in Statistics, vol. 190, Springer-Verlag, Berlin, 2007. Google Scholar

  • [24] M. Devilliers, Les enquêtes de conjoncture, Archives et Documents, no. 101, INSEE, 1984. Google Scholar

  • [25] E. Dubois and E. Michaux, étalonnages à l’aide d’enquêtes de conjoncture: de nouvaux résultats, Économie et Prévision, no. 172, INSEE, 2006. Google Scholar

  • [26] P. Doukhan, Mixing, Lecture Notes in Statistics, Springer, New York, 1994. Google Scholar

  • [27] K. Dowd, The inflation fan charts: An evaluation, Greek Economic Review 23 (2004), 99–111. Google Scholar

  • [28] A. Dalalyan and J. Salmon, Sharp oracle inequalities for aggregation of affine estimators, Ann. Statist. 40 (2012), no. 4, 2327–2355. CrossrefGoogle Scholar

  • [29] A. Dalalyan and A. Tsybakov, Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity, Mach. Learn. 72 (2008), 39–61. Google Scholar

  • [30] F. X. Diebold, A. S. Tay, and K. F. Wallis, Evaluating density forecasts of inflation: the survey of professional forecasters, Discussion Paper No.48, ESRC Macroeconomic Modelling Bureau, University of Warwick and Working Paper No.6228, National Bureau of Economic Research, Cambridge, Mass., 1997. Google Scholar

  • [31] M. D. Donsker and S. S. Varadhan, Asymptotic evaluation of certain markov process expectations for large time. iii., Comm. Pure Appl. Math. 28 (1976), 389–461. Google Scholar

  • [32] P. Doukhan and O. Wintenberger, Weakly dependent chain with infinite memory, Stochastic Process. Appl. 118 (2008), no. 11, 1997–2013. Google Scholar

  • [33] R. F. Engle, Autoregressive conditional heteroscedasticity with estimates of variance of united kingdom inflation, Econometrica 50 (1982), 987–1008. CrossrefGoogle Scholar

  • [34] C. Francq and J.-M. Zakoian, Garch models: Structure, statistical inference and financial applications, Wiley- Blackwell, 2010. Google Scholar

  • [35] S. Gerchinovitz, Sparsity regret bounds for individual sequences in online linear regression, Proceedings of COLT’11, 2011. Google Scholar

  • [36] J. Hamilton, Time series analysis, Princeton University Press, 1994. Google Scholar

  • [37] H. Hang and I. Steinwart, Fast learning from α-mixing observations, Technical report, Fakultät für Mathematik und Physik, Universität Stuttgart, 2012. Google Scholar

  • [38] I. A. Ibragimov, Some limit theorems for stationary processes, Theory Probab. Appl. 7 (1962), no. 4, 349–382. Google Scholar

  • [39] A. B. Juditsky, A. V. Nazin, A. B. Tsybakov, and N. Vayatis, Recursive aggregation of estimators bythe mirror descent algorithm with averaging, Probl. Inf. Transm. 41 (2005), no. 4, 368–384. CrossrefGoogle Scholar

  • [40] A. B. Juditsky, P. Rigollet, and A. B. Tsybakov, Learning my mirror averaging, Ann. Statist. 36 (2008), no. 5, 2183–2206. CrossrefGoogle Scholar

  • [41] R. Koenker and G. Jr. Bassett, Regression quantiles, Econometrica 46 (1978), 33–50. CrossrefGoogle Scholar

  • [42] R. Koenker, Quantile regression, Cambridge University Press, Cambridge, 2005. Google Scholar

  • [43] S. Kullback, Information theory and statistics, Wiley, New York, 1959. Google Scholar

  • [44] N. Littlestone and M.K. Warmuth, The weighted majority algorithm, Information and Computation 108 (1994), 212–261. Google Scholar

  • [45] P. Massart, Concentration inequalities and model selection - ecole d’été de probabilités de saint-flour xxxiii - 2003, Lecture Notes in Mathematics - J. Picard Editor, vol. 1896, Springer, 2007. Google Scholar

  • [46] D. A. McAllester, PAC-Bayesian model averaging, Procs. of of the 12th Annual Conf. On Computational Learning Theory, Santa Cruz, California (Electronic), ACM, New-York, 1999, pp. 164–170. Google Scholar

  • [47] R. Meir, Nonparametric time series prediction through adaptive model selection, Mach. Learn. 39 (2000), 5–34. Google Scholar

  • [48] C. Minodier, Avantages comparés des séries premières valeurs publiées et des séries des valeurs révisées, Documents de Travail de la DESE, 2010. Google Scholar

  • [49] D. S. Modha and E. Masry, Memory-universal prediction of stationary random processes, IEEE Trans. Inform. Theory 44 (1998), no. 1, 117–133. CrossrefGoogle Scholar

  • [50] S. P. Meyn and R. L. Tweedie, Markov chains and stochastic stability, Communications and Control Engineering Series, Springer-Verlag London Ltd., London, 1993. MR 1287609 (95j:60103) Google Scholar

  • [51] A. Nemirovski, Topics in nonparametric statistics, Lectures on Probability Theory and Statistics - Ecole d’ét’e de probagilités de Saint-Flour XXVIII (P. Bernard, ed.), Springer, 2000, pp. 85–277. Google Scholar

  • [52] R Development Core Team, R: A language and environment for statistical computing, R Foundation for Statistical Computing, Vienna, 2008. Google Scholar

  • [53] E. Rio, Ingalités de Hoeffding pour les fonctions lipschitziennes de suites dépendantes, C. R. Math. Acad. Sci. Paris 330 (2000), 905–908. Google Scholar

  • [54] P.-M. Samson, Concentration of measure inequalities for markov chains and φ-mixing processes, Ann. Probab. 28 (2000), no. 1, 416–461. Google Scholar

  • [55] I. Steinwart and A. Christmann, Fast learning from non-i.i.d. observations, Advances in Neural Information Processing Systems 22 (Y. Bengio, D. Schuurmans, J. Lafferty, C. K. I. Williams, and A. Culotta, eds.), 2009, pp. 1768–1776. Google Scholar

  • [56] I. Steinwart, D. Hush, and C. Scovel, Learning from dependent observations, J. Multivariate Anal. 100 (2009), 175–194. CrossrefGoogle Scholar

  • [57] Y. Seldin, F. Laviolette, N. Cesa-Bianchi, J. Shawe-Taylor, J. Peters, and P. Auer, Pac-bayesian inequalities for martingales, IEEE Trans. Inform. Theory 58 (2012), no. 12, 7086–7093. CrossrefGoogle Scholar

  • [58] A. Sanchez-Perez, Time series prediction via aggregation : an oracle bound including numerical cost, Preprint arXiv:1311.4500, 2013. Google Scholar

  • [59] G. Stoltz, Agrégation séquentielle de prédicteurs : méthodologie générale et applications à la prévision de la qualité de l’air et à celle de la consommation électrique, Journal de la SFDS 151 (2010), no. 2, 66–106. Google Scholar

  • [60] J. Shawe-Taylor and R. Williamson, A PAC analysis of a bayes estimator, Proceedings of the Tenth Annual Conference on Computational Learning Theory, COLT’97, ACM, 1997, pp. 2–9. Google Scholar

  • [61] N. N. Taleb, Black swans and the domains of statistics, Amer. Statist. 61 (2007), no. 3, 198–200. Google Scholar

  • [62] A. S. Tay and K. F. Wallis, Density forecasting: a survey, J. Forecast 19 (2000), 235–254. Google Scholar

  • [63] V. Vapnik, The nature of statistical learning theory, Springer, 1999. Google Scholar

  • [64] V.G. Vovk, Aggregating strategies, Proceedings of the 3rd Annual Workshop on Computational Learning Theory (COLT), 1990, pp. 372–283. Google Scholar

  • [65] O. Wintenberger, Deviation inequalities for sums of weakly dependent time series, Electron. Commun. Probab. 15 (2010), 489–503. Google Scholar

  • [66] Y.-L. Xu and D.-R. Chen, Learning rate of regularized regression for exponentially strongly mixing sequence, J. Statist. Plann. Inference 138 (2008), 2180–2189. Google Scholar

  • [67] B. Zou, L. Li, and Z. Xu, The generalization performance of erm algorithm with strongly mixing observations, Mach. Learn. 75 (2009), 275–295. Google Scholar

About the article

Received: 2013-10-23

Accepted: 2013-12-08

Published Online: 2013-12-31

Citation Information: Dependence Modeling, Volume 1, Pages 65–93, ISSN (Online) 2300-2298, DOI: https://doi.org/10.2478/demo-2013-0004.

Export Citation

©2013 Olivier Wintenberger et al.. This article is distributed under the terms of the Creative Commons Attribution Non-Commercial No-Derivatives License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. BY-NC-ND 3.0

Citing Articles

Here you can find all Crossref-listed publications in which this article is cited. If you would like to receive automatic email messages as soon as this article is cited in other publications, simply activate the “Citation Alert” on the top of this page.

Pierre Alquier and Benjamin Guedj
Machine Learning, 2017
Olivier Wintenberger
Machine Learning, 2017, Volume 106, Number 1, Page 119

Comments (0)

Please log in or register to comment.
Log in