×

Sparse inference of the drift of a high-dimensional Ornstein-Uhlenbeck process. (English) Zbl 1404.60049

Summary: Given the observation of a high-dimensional Ornstein-Uhlenbeck (OU) process in continuous time, we are interested in inference on the drift parameter under a row-sparsity assumption. Towards that aim, we consider the negative log-likelihood of the process, penalized by an \(\ell^1\)-penalization (Lasso and Adaptive Lasso). We provide both finite- and large-sample results for this procedure, by means of a sharp oracle inequality, and a limit theorem in the long-time asymptotics, including asymptotic consistency for variable selection. As a by-product, we point out the fact that for the Ornstein-Uhlenbeck process, one does not need an assumption of restricted eigenvalue type in order to derive fast rates for the Lasso, while it is well-known to be mandatory for linear regression for instance. Numerical results illustrate the benefits of this penalized procedure compared to standard maximum likelihood approaches both on simulations and real-world financial data.

MSC:

60G15 Gaussian processes
62H12 Estimation in multivariate analysis
62M99 Inference from stochastic processes

References:

[1] Bach, F.; Jenatton, R.; Mairal, J.; Obozinski, G., Optimization with sparsity-inducing penalties, Found. Trends ^{®} Mach. Learn., 4, 1-106, (2012) · Zbl 06064248
[2] Basu, S.; Michailidis, G., Regularized estimation in sparse high-dimensional time series models, Ann. Statist., 43, 1535-1567, (2015) · Zbl 1317.62067
[3] Bellec, P. C.; Lecué, G.; Tsybakov, A. B., Slope meets lasso: Improved oracle bounds and optimality, Ann. Statist., (2018) · Zbl 1405.62056
[4] Bickel, P. J.; Ritov, Y.; Tsybakov, A. B., Simultaneous analysis of lasso and Dantzig selector, Ann. Statist., 37, 1705-1732, (2009) · Zbl 1173.62022
[5] F. Blasques, F. Bräuning, I. van Lelyveld, A dynamic network model of the unsecured interbank lending market, BIS Working Papers 491, Bank for International Settlements, 2015.; F. Blasques, F. Bräuning, I. van Lelyveld, A dynamic network model of the unsecured interbank lending market, BIS Working Papers 491, Bank for International Settlements, 2015.
[6] Bühlmann, P.; van de Geer, S., Statistics for High-Dimensional Data: Methods, Theory and Applications, (2011), Springer: Springer Heidelberg · Zbl 1273.62015
[7] Bunea, F.; She, Y.; Wegkamp, M. H., Optimal selection of reduced rank estimators of high-dimensional matrices, Ann. Statist., 39, 1282-1309, (2011) · Zbl 1216.62086
[8] Bunea, F.; She, Y.; Wegkamp, M. H., Joint variable and rank selection for parsimonious estimation of high-dimensional matrices, Ann. Statist., 40, 2359-2388, (2012) · Zbl 1373.62246
[9] Carmona, R.; Fouque, J.-P.; Sun, L.-H., Mean field games and systemic risk, Commun. Math. Sci., 13, 911-933, (2015) · Zbl 1337.91031
[10] Cattiaux, P.; Guillin, A., Deviation bounds for additive functionals of Markov processes, ESAIM: Probab. Statist., 12, 12-29, (2007) · Zbl 1183.60011
[11] Erdős, P.; Gallai, T., Gráfok előírt fokszámú pontokkal, Mat. Lapok, 11, 264-274, (1960) · Zbl 0103.39701
[12] Fouque, J.-P.; Ichiba, T., Stability in a model of interbank lending, SIAM J. Financial Math., 4, 784-803, (2013) · Zbl 1295.91099
[13] S. Gabrieli, C.-P. Georg, A Network View on Interbank Market Freezes, Technical Report, Banque de France, 2014.; S. Gabrieli, C.-P. Georg, A Network View on Interbank Market Freezes, Technical Report, Banque de France, 2014.
[14] Gabrieli, S.; Salakhova, D., Cross-border interbank contagion in the European banking sector, Int. Econ., (2018)
[15] Giraud, C., Introduction to High-Dimensional Statistics, (2015), CRC Press: CRC Press Boca Raton, FL · Zbl 1341.62011
[16] E. Gobet, Q. She, Perturbation of Ornstein-Uhlenbeck stationary distributions: Expansion and simulation, 2016. Working paper.; E. Gobet, Q. She, Perturbation of Ornstein-Uhlenbeck stationary distributions: Expansion and simulation, 2016. Working paper.
[17] Gross, L., Logarithmic Sobolev inequalities, Amer. J. Math., 97, 1061-1083, (1975) · Zbl 0318.46049
[18] Hull, J. C., Options, Futures and Other Derivatives, (2009), Pearson/Prentice Hall: Pearson/Prentice Hall Upper Saddle River, NJ · Zbl 1087.91025
[19] Hwang, C.-R.; Hwang-Ma, S.-Y.; Sheu, S.-J., Accelerating gaussian diffusions, Ann. Appl. Probab., 3, 897-913, (1993) · Zbl 0780.60074
[20] Jacod, J., Inference for Stochastic Processes, Prépublications Du Laboratoire de Probabilités et Modèles Aléatoires, (2001), Université Pierre-et-Marie-Curie: Université Pierre-et-Marie-Curie Paris, France
[21] Karatzas, I.; Shreve, Steven E., Brownian Motion and Stochastic Calculus, (1991), Springer: Springer New York · Zbl 0734.60060
[22] Klopp, O.; Tsybakov, A. B., Estimation of matrices with row sparsity, Probl. Inf. Transm., 51, 335-348, (2015) · Zbl 1388.62161
[23] Kutoyants, Y. A., Statistical Inference for Ergodic Diffusion Processes, (2004), Springer: Springer New York · Zbl 1038.62073
[24] McKay, B. D.; Wormald, N. C., Asymptotic enumeration by degree sequence of graphs with degrees \(o(\sqrt{n})\), Combinatorica, 11, 369-382, (1991) · Zbl 0742.05047
[25] Revuz, D.; Yor, M., Continuous Martingales and Brownian Motion, (1999), Springer: Springer Berlin Heidelberg · Zbl 0917.60006
[26] Sokol, A., On martingales, Causality, Identifiability and Model Selection, (2013), University of Copenhagen: University of Copenhagen Danemark, (Ph.D. thesis)
[27] Su, W.; Candès, E., Slope is adaptive to unknown sparsity and asymptotically minimax, Ann. Statist., 44, 1038-1068, (2016) · Zbl 1338.62032
[28] Tibshirani, R. J., Regression shrinkage and selection via the lasso, J. R. Stat. Soc. Ser. B Stat. Methodol., 58, 267-288, (1996) · Zbl 0850.62538
[29] Tsybakov, A. B., Introduction to Nonparametric Estimation, (2008), Springer: Springer New York
[30] van Zanten, H., A multivariate central limit theorem for continuous local martingales, Statist. Probab. Lett., 50, 229-235, (2000) · Zbl 1004.60020
[31] Y. Zhang, M.J. Wainwright, M.I. Jordan, Lower bounds on the performance of polynomial-time algorithms for sparse linear regression, in: Proceedings of the 27th Conference on Learning Theory, COLT 2014, Barcelona, Spain, June 13-15, 2014, pp. 921-948.; Y. Zhang, M.J. Wainwright, M.I. Jordan, Lower bounds on the performance of polynomial-time algorithms for sparse linear regression, in: Proceedings of the 27th Conference on Learning Theory, COLT 2014, Barcelona, Spain, June 13-15, 2014, pp. 921-948.
[32] Zou, H., The adaptive lasso and its oracle properties, J. Amer. Statist. Assoc., 101, 1418-1429, (2006) · Zbl 1171.62326
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.