, ? NousétudionsNousétudions la performance des algorithmes d'apprentissage via une minimisation empirique du risque. Il estàestà noter que l'analyse de l'algorithme ERM et des propriétés des algorithmes d'apprentissage statistique sont desprobì emes très importants et urgentsàgentsà résoudre

, ? NousétudionsNousétudions les propriétés de généralisation d'un algorithme d'apprentissage statistique sélectionné

, estimation de MV-set peutêtrepeutêtre transposée dans un cadre d'apprentissage très semblablè a la minimisation empirique du risque dans la classification (supervisée), vol.126

, Dans toute cette section, I A est la fonction indicatrice de l'´ evénement A. On suppose que X = (X n ) n?N est une cha??necha??ne de Markov homogène sur un espace d'´ etat général (E, E) avec probabilité de transition ? et loi initiale ?. Le lecteur pourra noter que Fevrier 2016, Présentation au Workshop COmputational Statistics and MOlecular Simulation, Le lecteur intéressé trouvera dans la littérature susmentionnée les preuves des théorèmes théorèmesénoncés pour des cha??nescha??nes de MarkovàMarkovà espace d'´ etat général, 2016.

R. Adamczak, A tail inequality for suprema of unbounded empirical processes with applications to Markov chains, Electronic Journal of Probability, vol.34, pp.1000-10034, 2008.

R. Adamczak and W. Bednorz, Exponential concentration inequalities for additive functionals of Markov chains, ESAIM: Probability and Statistics, vol.19, pp.440-481, 2015.

T. M. Adams and A. B. Nobel, Uniform convergence of Vapnik-Chervonenkis classes under ergodic sampling, Annals of Probability, vol.38, pp.1345-1367, 2010.

A. Agarwal and J. Duchi, The generalization ability of online algorithms for dependent data, IEEE Transactions on Information Theory, vol.59, pp.573-587, 2013.

P. Alquier and O. Wintenberger, Model selection for weakly dependent time series forecasting, Bernoulli, vol.18, pp.883-913, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00717618

G. Alsmeyer, On the Harris recurrence and iterated random Lipschitz functions and related convergence rate results, Journal of Theoretical Probability, vol.16, pp.217-247, 2003.

R. Arora, W. Sethares, and J. Bucklew, Latent periodicities in genome sequences, IEEE Journal of Selected Topics in Signal Processing, vol.2, pp.332-342, 2008.

S. Asmussen and H. Albrecher, Ruin Probabilities. Applications of Mathematics, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00569254

K. Athreya and G. Atuncar, Kernel estimation for real-valued Markov chains, The Indian Journal of Statistics, Series A, vol.60, pp.1-17, 1998.

K. B. Athreya and C. D. Fuh, Bootstrapping Markov chains: countable case, Journal of Statistical Planning and Inference, vol.33, pp.311-331, 1992.

K. B. Athreya and C. D. Fuh, Central limit theorem for a double array of Harris chains, The Indian Journal of Statistics, Series A, vol.55, pp.1-11, 1993.

K. B. Athreya and P. Ney, A new approach to the limit theory of recurrent Markov chains, Transactions of the American Mathematical Society, vol.245, pp.493-501, 1978.

K. B. Athreya and S. G. Pantula, Mixing properties of Harris chains and autoregressive processes, Journal of Applied Probability, vol.23, pp.880-892, 1986.

R. Aza¨?saza¨?s and F. Bouguet, Statistical Inference for Piecewise-deterministic Markov Processes, 2018.

Z. Bai and Z. Lin, Probability Inequalities, 2009.

Y. Baraud, Bounding the expectation of the supremum of an empirical process over a (weak) VC-major class, Electronic Journal of Statistics, vol.10, pp.1709-1728, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01085004

P. Barbe and P. Bertail, The Weighted Bootstrap. Lecture Notes in Statistics, 1995.

P. Barbe, A. Fougeres, and C. Genest, On the tail behavior of sums of dependent risks, Astin Bulletin, vol.36, pp.361-373, 2006.
URL : https://hal.archives-ouvertes.fr/hal-00097051

I. V. Basawa and R. B. Lund, Recursive prediction and likelihood evaluation for periodic ARMA models, Journal of Time Series Analysis, vol.21, pp.75-93, 2000.

I. V. Basawa and R. B. Lund, Large sample properties of parameter for periodic ARMA models, Journal of Time Series Analysis, vol.21, pp.75-93, 2001.

J. Berkowitz and L. Kilian, Recent developments in bootstrapping time series, Econometric Reviews, vol.19, pp.1-54, 2000.

P. Bertail and G. Cio?, New Bernstein and Hoeffding type inequalities for regenerative Markov chains, Accepted in Latin American Journal of Probability and Mathematical Statistics, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01440167

P. Bertail, G. Cio?, and S. Clémençon, Generalization bounds for minimum volume set estimation based on Markovian data, ISAIM, International Symposium on Artificial Intelligence and Mathematics Proceedings Book, pp.1-7, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01738026

P. Bertail, G. Cio?, and S. Clémençon, Statistical learning based on Markovian data. Maximal deviation inequalities and learning rates, 2018.

P. Bertail, G. Cio?, and C. Tillier, Robust estimation for Markov chains with application to PDMP, Statistical Inference for Piecewise-Deterministic Markov Processes, 2018.

P. Bertail and S. Clémençon, Regenerative block bootstrap for Markov chains, Bernoulli, vol.12, pp.689-712, 2005.
URL : https://hal.archives-ouvertes.fr/hal-02107125

P. Bertail and S. Clémençon, Regeneration-based statistics for Harris recurrent Markov chains. Dependence in Probability and Statistics, Lecture Notes in Statistics, 2006.
URL : https://hal.archives-ouvertes.fr/hal-02107054

P. Bertail and S. Clémençon, Sharp bounds for the tails of functionals of Markov chains, Theory of Probability and Its Applications, vol.54, pp.505-515, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00140591

P. Bertail and S. Clémençon, Bootstrapping robust statistics for Markovian data. Applications to regenerative R-and L-statistics, Journal of Time Series Analysis, vol.36, pp.462-480, 2015.
URL : https://hal.archives-ouvertes.fr/hal-02107439

P. Bertail, S. Clémençon, and C. Tillier, Extreme values statistics for Markov chains with applications to finance and insurance. Extreme Events in Finance: A Handbook of Extreme Value Theory and its Applications, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01709875

P. Bertail, S. Clémençon, and J. Tressou, A storage model for modelling exposure to food contaminants, Mathematical Biosciences and Engineering, vol.5, pp.35-60, 2006.

P. Bertail, S. Clémençon, and J. Tressou, Extreme value statistics for Markov chains via the (pseudo-) regenerative method, Extremes, vol.12, pp.327-360, 2009.

P. Bertail, S. Clémençon, and J. Tressou, Regenerative block-bootstrap confidence intervals for the tail and extremal indexes, Electronic Journal of Statistics, vol.7, pp.1224-1248, 2013.
URL : https://hal.archives-ouvertes.fr/hal-01069874

A. Bibi and I. Lescheb, A note on integrated periodic garch processes, Statistics and Probability Letters, vol.87, pp.121-124, 2014.

P. Bickel and J. Kwon, Inference for semiparametric models: Some current frontiers, Statistica Sinica, vol.11, pp.863-960, 2001.

E. Bolthausen, The Berry-Essen theorem for strongly mixing Harris recurrent Markov chains. Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete, vol.60, pp.283-289, 1982.

S. Boucheron, G. Lugosi, and P. Massart, Inequalities. A Nonasymptotic Theory of Independence, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00751496

O. Bousquet, S. Boucheron, and G. Lugosi, Introduction to statistical learning theory, Advanced Lectures on Machine Learning, 2004.

P. J. Brockwell and R. A. Davis, Introduction to Time Series and Forecasting, 2002.

E. Broszkiewicz-suwaj, A. Makagon, R. Weron, and A. Wy?, On detecting and modeling periodic correlation in financial data, Physica A: Statistical Mechanics and its Applications, vol.336, pp.196-205, 2004.

J. R. Chazottes and F. Redig, Concentration inequalities for Markov processes via coupling, Electronic Journal of Probability, vol.14, pp.1162-1180, 2009.

V. Chernozhukov, D. Chetverikov, and K. Kato, Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors, The Annals of Statistics, vol.41, pp.2786-2819, 2013.

V. Chernozhukov, D. Chetverikov, and K. Kato, Central limit theorems and bootstrap in high dimensions, The Annals of Probability, vol.45, pp.2309-2352, 2017.

G. Cio?, Bootstrap uniform central limit theorems for Harris recurrent Markov chains, Electronic Journal of Statistics, vol.10, pp.2157-2178, 2016.

G. Cio?, Bootstrapping Harris recurrent Markov chains, Springer Proceedings in Mathematics and Statistics, 2016.

G. Cio?-lek and P. Potorski, Bootstrapping periodically autoregressive models, ESAIM: Probability and Statistics, vol.21, pp.2157-2178, 2017.

S. Clémençon, Moment and probability inequalities for sums of bounded additive functionals of a regular Markov chains via the Nummelin splitting technique, Statistics and Probability Letters, vol.55, pp.227-238, 2001.

S. Clémençon, P. Bertail, and G. Papa, Learning from survey training samples: rate bounds for Horvitz-Thompson risk minimizers, Proceedings of ACML'16, 2016.

F. Cucker and S. Smale, On the mathematical foundations of learning, Bulletin of the American Mathematical Society, vol.39, pp.1-49, 2002.

S. Datta and W. Mccormick, Some continuous Edgeworth expansions for Markov chains with applications to bootstrap, Journal of Multivariate Analysis, vol.52, pp.83-106, 1995.

M. H. Davis, Piecewise-deterministic Markov processes: A general class of nondiffusion stochastic models, Journal of the Royal Statistical Society. Series B, vol.46, pp.353-388, 1984.

V. De-la-pena and E. Giné, Decoupling: from Dependence to Independence, 1999.

J. Dedecker and S. Gouëzel, Subgaussian concentration inequalities for geometrically ergodic Markov chains, Electronic Communications in Probability, vol.20, pp.1-12, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01091212

H. Dehling, T. Mikosch, and M. Sørensen, Empirical Process Techniques for Dependent Data, 2002.
URL : https://hal.archives-ouvertes.fr/hal-00291501

J. Di and E. Kolaczyk, Complexity-penalized estimation of minimum volume sets for dependent data, Journal of Multivariate Analysis, vol.101, pp.1910-1926, 2004.

J. Dowell, S. Weiss, D. Hill, and D. Infield, A cyclo-stationary complex multichannel Wiener filter for the prediction of wind speed and direction, Proceedings of the 21st

, European Signal Processing Conference, 2013.

R. Duc, E. Moulines, and P. Soulier, Computable convergence rates for sub-geometric ergodic Markov chains, Bernoulli, vol.13, pp.831-848, 2007.

R. M. Dudley, Nonlinear functionals of empirical measures and the bootstrap. Probability in Banach Spaces, Birkhäuser, vol.7, pp.63-82, 1990.

B. Efron, Bootstrap methods: another look at the jacknife, Annals of Statistics, vol.7, pp.1-26, 1979.

B. Efron and R. Tibshirani, Bootstrap methods for standard errors, confidence intervals and other measures of statistical accuracy, Statistical Science, vol.1, pp.54-77, 1986.

J. H. Einmahl and D. M. Mason, Generalized quantile process, The Annals of Statistics, vol.20, pp.1062-1078, 1992.

P. Embrechts, C. Kluppelberg, and T. Mikosch, Modelling Extremal Events for Insurance and Finance, 1997.

V. Feuillard, A. Gramfort, and A. Thomas, Calibration of one-class SVM for MV set estimation, IEEE International Conference on Data Science and Advanced Analytics, 1998.
URL : https://hal.archives-ouvertes.fr/hal-01188294

J. Friedman, T. Hastie, and R. Tibshirani, The Elements of Statistical Learning, 2009.

F. Gao and L. Wu, Bernstein type's concentration inequalities for symmetric Markov processes, Theory of Probability and its Applications, vol.58, pp.358-382, 2014.

C. Gaucherel, Analysis of enso interannual oscillations using non-stationary quasiperiodic statistics, International Journal of Climatology, vol.30, pp.926-934, 2010.

F. Ghaderi, K. Nazarpour, J. G. Mcwhirter, and S. Sanei, Removal of ballistocardiogram artifacts using the cyclostationary source extraction method, IEEE Transactions on Biomedical Engineering, vol.57, pp.2667-2676, 2010.

E. Giné and R. Nickl, Uniform central limit theorems for kernel density estimators, Probability Theory and Related Fields, vol.141, pp.333-387, 2008.

E. Giné and R. Nickl, Uniform limit theorems for wavelet density estimators, The Annals of Probability, vol.37, pp.1605-1646, 2009.

E. Giné and V. Koltchinskii, Concentration inequalities and asymptotic results for ratio type empirical processes. The Annals of Probability, vol.34, pp.1143-1216, 2006.

E. Giné and J. Zinn, Some limit theorems for empirical processes, The Annals of Probability, vol.12, pp.929-989, 1984.

E. Giné and J. Zinn, Bootstrapping general empirical measures. The Annals of Probability, vol.18, pp.851-869, 1990.

E. G. Glady?hev, Periodically correlated random sequences, Soviet Mathematics, vol.2, pp.385-388, 1961.

P. W. Glynn and D. Ormoneit, Hoeffding's inequality for uniformly ergodic Markov chains, Statistics and Probability Letters, vol.56, pp.143-146, 2002.

A. Gorst-rasmussen and M. Bøgsted, Asymptotic inference for waiting times and patiences in queues with abandonment, Statistics-Simulation and Computation, vol.38, pp.318-334, 2009.
URL : https://hal.archives-ouvertes.fr/hal-00514337

P. Hall, The Bootstrap and Edgeworth Expansion, 1992.

J. D. Hamilton, Time Series Analysis, 1994.

S. Hanneke, Learning whenever learning is possible: Universal learning under general stochastic processes, 2017.

W. Hoeffding, Probability inequalities for sums of bounded random variables, Journal of the American Statistical Association, vol.58, pp.13-30, 1963.

J. L. Horovitz, The bootstrap. Handbook of Econometrics, vol.5, pp.3159-3228, 2001.

B. Iqelan, Periodically Correlated Time Series: Models and Examples, 2011.

J. Jain and B. Jamison, Contributions to Doeblin's theory of Markov processes. Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete, vol.8, pp.19-40, 1964.

R. H. Jones and W. M. Brelsford, Time series with periodic structure, Biometrika, vol.54, pp.403-408, 1967.

K. Y. Kim, B. Hamilton, and H. Na, Theoretical foundation of cyclostationary EOF analysis for geophysical and climatic variables, Concepts and Examples, Earth-Science Reviews, vol.150, pp.201-218, 2015.

A. Klenke, Probability Theory

I. Kontoyiannis and S. P. Meyn, Geometric ergodicity and the spectral gap of nonreversible Markov chains, Probability Theory and Related Fields, vol.154, pp.327-339, 2012.

M. R. Kosorok, Introduction to Empirical Processes and Semiparametric Inference, 2008.

J. Kreiss and S. Lahiri, Bootstrap methods for time series, Time Series Analysis: Methods and Applications, vol.30, pp.3-23, 2012.

J. Kreiss and E. Paparoditis, Bootstrap methods for dependent data: A review, Journal of the Korean Statistical Society, vol.40, pp.357-378, 2011.

H. Kunsch, Infinitesimal robustness for autoregressive processes, The Annals of Statistics, vol.12, pp.843-863, 1984.

V. Kuznetsov and M. Mohri, Generalization bounds for time series prediction with non-stationary processes, Proceedings of ALT'14, 2014.

A. Kyprianou and S. Gerber, Risk Theory. EAA Series Springer International Publishing, 2013.

S. Lahiri, Resampling methods for Dependent Data, 2003.

S. N. Lahiri, Theoretical comparisons of block bootstrap methods. The Annals of Statistics, vol.27, pp.386-404, 1999.

K. Latuszy´nskilatuszy´nski, Regeneration and Fixed-Width Analysis of Markov Chain Monte Carlo Algorithms, 2008.

M. R. Leadbetter and H. Rootzen, Extremal theory for stochastic processes, The Annals of Probability, vol.16, pp.431-478, 1988.

J. Lederer and S. Van-der-geer, New concentration inequalities for suprema of empirical processes, Bernoulli, vol.20, pp.2020-2038, 2014.

S. , Uniform limit theorems for Harris recurrent Markov chains. Probability Theory and Related Fields, vol.80, pp.101-118, 1988.

P. Lezaud, Chernoff and Berry-Esseen inequalities for Markov processes, ESAIM: Probability and Statistics, vol.5, pp.183-201, 2001.
URL : https://hal.archives-ouvertes.fr/hal-00940906

R. Liu, Bootstrap procedures under some non-i.i.d. models. The Annals of Statistics, vol.16, pp.1696-1708, 2008.

S. Maiz, . El, F. Badaoui, C. Bonnardot, and . Serviere, New second order cyclostationary analysis and application to the detection and characterization of a runner's fatigue, Signal Processing, vol.102, pp.188-200, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01122607

K. V. Mardia, Multivariate Pareto distributions, Annals of Mathematical Statistics, vol.33, pp.1008-1015, 1962.

R. D. Martin and V. J. Yohai, Influence functionals for time series, The Annals of Statistics, vol.14, pp.781-818, 1986.

P. Massart, Some applications of concentration inequalities to statistics, vol.9, pp.245-303, 2000.

F. Merlevède and M. Peligrad, Rosenthal-type inequalities for the maximum of partial sums of stationary processes and examples, vol.41, pp.914-960, 2013.

S. P. Meyn and R. L. Tweedie, Markov Chains and Stochastic Stability, 1993.

T. Mikosch, Non-life Insurance Mathematics, 2010.

S. J. Montgomery-smith, Comparison of sums of independent identically distributed random vectors, Probability and Mathematical Statistics, vol.14, issue.2, pp.281-285, 1993.

U. Muller, A. Schick, and W. Wefelmeyer, Improved estimators for constrained Markov chain models, Statistics and Probability Letters, vol.54, pp.427-435, 2001.

R. , Donsker-type theorems for nonparametric maximum likelihood estimators. Probability Theory and Related Fields, vol.138, pp.411-449, 2007.

E. Nummelin, Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete, vol.43, pp.309-318, 1978.

E. Nummelin, General irreducible Markov chains and non-negative operators, 1984.

M. Pagano, On periodic and multiple autoregressions, The Annals of Statistics, vol.6, pp.1310-1317, 1978.

D. Paulin, Concentration inequalities for Markov chains by Marton couplings and spectral methods, Electronic Journal of Probability, vol.20, pp.1-32, 2015.

M. Peligrad, The r-quick version of the strong law for stationary ?-mixing sequences, Almost Everywhere Convergence, 1988.

J. C. Pereau and E. Ursu, Application of periodic autoregressive process to the modeling of the garonne river flows, Stochastic Environmental Research and Risk Assessment, vol.30, pp.1785-1795, 2016.

R. Perfekt, Extremal behaviour of stationary Markov chains with applications, The Annals of Applied Probability, vol.4, pp.529-548, 1994.

V. V. Petrov, Limit Theorems of Probability Theory: Sequences of Independent Random Variables. Oxford studies in probability, 1995.

D. Pollard, Convergence of Stochastic Processes, Springer Series in Statistics, 1984.

W. Polonik, Minimum volume sets and generalized quantile processes, Stochastic Processes and their Applications, vol.69, pp.1-24, 1997.

D. Radulovi´cradulovi´c, On the bootstrap and empirical processes for dependent sequences, Empirical Process Techniques for Dependent Data, Birkhäuser, pp.345-364, 2002.

D. Radulovi´cradulovi´c, Renewal type bootstrap for Markov chains, TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, vol.13, pp.147-192, 2004.

S. I. Resnick, Extreme Values, Regular Variation and Point Processes, 1987.

H. Rieder, Robust Asymptotic Statistics, 1994.

H. Rootzen, Maxima and exceedances of stationary Markov chains, Advances in Applied Probability, vol.20, pp.371-390, 1988.

C. Scott and R. Nowak, Learning minimum volume sets, Journal of Machine Learning Research, vol.7, pp.665-704, 2006.

C. Scott and R. Nowak, Minimax-optimal classification with dyadic decision trees, IEEE Transactions on Information Theory, vol.52, pp.1335-1353, 2006.

B. Sen, A Study of Bootstrap and Likelihood Based Methods in Non-Standard Problems, 2008.

Q. Shao, Maximal inequalities for partial sums of ?-mixing sequences, The Annals of Probability, vol.23, pp.948-965, 1995.

Q. Shao and P. P. Ni, Least-squares estimation and ANOVA for periodic autoregressive time series, Statistics and Probability Letters, vol.69, pp.287-297, 2004.

K. Shimizu, Boostrapping Stationary ARMA-GARCH Models. Vieweg+Teubner Research, 2009.

I. Steinwart and A. Christmann, Fast learning from non-i.i.d. observations. NIPS, pp.1768-1776, 2009.

I. Steinwart, D. Hush, and C. Scovel, Learning from dependent observations, Journal of Multivariate Analysis, vol.100, issue.1, pp.175-194, 2009.

R. A. Stine, Estimating properties of autoregressive forecasts, Journal of the Ametican Statistical Association, vol.82, pp.1072-1078, 1987.

G. B. Thomas and D. F. Fiering, Mathematical synthesis of stream flow sequences for the analysis of river basins by simulation, Design of Water Resources Systems, 1962.

H. Thorisson, Coupling, Stationarity and Regeneration, 2000.

T. H. Tsai, The Uniform CLT and LIL for Markov Chains, 1998.

E. Ursu and P. Duchesne, On modelling and diagnostic checking of vector periodic autoregressive time series models, Journal of Time Series Analysis, vol.30, pp.70-96, 2009.

S. A. Utev, Sums of random variables with ?-mixing, Siberian Advances in Mathematics, vol.1, pp.124-155, 1991.

A. Van-der and . Vaart, Asymptotic Statistics, 1998.

A. W. Van-der-vaart and J. A. Wellner, Weak Convergence and Empirical Processes, 1996.

V. Vapnik, Statistical Learning Theory, 1998.

V. N. Vapnik, The Nature of Statistical Learning Theory, 1999.

V. N. Vapnik, An overview of statistical learning theory, IEEE Transactions on Neural Networks, vol.10, pp.988-999, 1999.

A. Vecchia, Maximum likelihood estimation for periodic autoregressive moving average models, vol.27, pp.375-384, 1985.

G. Viennet, Inequalities for absolutely regular sequences: Application to density estimation, Probability Theory and Related Fields, vol.107, pp.467-492, 1997.

T. D. Wet and J. W. Van-wyk, Bootstrap confidence intervals for regression coefficients when the residuals are dependent, Journal of Statistical Computation and Simulation, vol.23, pp.317-327, 1986.

O. Wintenberger, Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms, A Journal of Theoretical and Applied Statistics, vol.51, pp.222-234, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01222870

B. Zou, H. Zhang, and Z. B. Xu, Learning from uniformly ergodic Markov chain samples, Journal of Complexity, vol.25, pp.188-200, 2009.