IDEAS home Printed from https://ideas.repec.org/p/crs/wpaper/2017-30.html

Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions

Author

Listed:
  • Pierre Alquier

    (CREST; ENSAE; Université Paris Saclay)

  • Vincent Cottet

    (CREST; ENSAE; Université Paris Saclay)

  • Guillaume Lecué

    (CREST; CNRS; Université Paris Saclay)

Abstract

We obtain estimation error rates and sharp oracle inequalities for regularization procedures of the form [See the abstract on the paper for the formula] when ||.|| is any norm, F is a convex class of functions and l is a Lipschitz loss function satisfying a Bernstein condition over F. We explore both the bounded and subgaussian stochastic frameworks for the distribution of the f(Xi)'s, with no assumption on the distribution of the Yi's. The general results rely on two main objects: a complexity function, and a sparsity equation, that depend on the specific setting in hand (loss l and norm ||.||). As a proof of concept, we obtain minimax rates of convergence in the following problems: 1) matrix completion with any Lipschitz loss function, including the hinge and logistic loss for the so-called 1-bit matrix completion instance of the problem, and quantile losses for the general case, which enables to estimate any quantile on the entries of the matrix; 2) logistic LASSO and variants such as the logistic SLOPE; 3) kernel methods, where the loss is the hinge loss, and the regularization function is the RKHS norm.

Suggested Citation

  • Pierre Alquier & Vincent Cottet & Guillaume Lecué, 2017. "Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions," Working Papers 2017-30, Center for Research in Economics and Statistics.
    • Handle: RePEc:crs:wpaper:2017-30
    as

    Download full text from publisher

    File URL: http://crest.science/RePEc/wpstorage/2017-30.pdf
    File Function: CREST working paper version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Alexandre Belloni & Victor Chernozhukov, 2009. "L1-Penalized quantile regression in high-dimensional sparse models," CeMMAP working papers CWP10/09, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    2. Garcia-Magariños Manuel & Antoniadis Anestis & Cao Ricardo & González-Manteiga Wenceslao, 2010. "Lasso Logistic Regression, GSoft and the Cyclic Coordinate Descent Algorithm: Application to Gene Expression Data," Statistical Applications in Genetics and Molecular Biology, De Gruyter, vol. 9(1), pages 1-30, August.
    3. Lukas Meier & Sara Van De Geer & Peter Bühlmann, 2008. "The group lasso for logistic regression," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 70(1), pages 53-71, February.
    4. Bartlett, Peter L. & Jordan, Michael I. & McAuliffe, Jon D., 2006. "Convexity, Classification, and Risk Bounds," Journal of the American Statistical Association, American Statistical Association, vol. 101, pages 138-156, March.
    5. Tian, Guo-Liang & Tang, Man-Lai & Fang, Hong-Bin & Tan, Ming, 2008. "Efficient methods for estimating constrained parameters with applications to regularized (lasso) logistic regression," Computational Statistics & Data Analysis, Elsevier, vol. 52(7), pages 3528-3542, March.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Diego Vidaurre & Concha Bielza & Pedro Larrañaga, 2013. "A Survey of L1 Regression," International Statistical Review, International Statistical Institute, vol. 81(3), pages 361-387, December.
    2. Luis M. Briceño-Arias & Giovanni Chierchia & Emilie Chouzenoux & Jean-Christophe Pesquet, 2019. "A random block-coordinate Douglas–Rachford splitting method with low computational complexity for binary logistic regression," Computational Optimization and Applications, Springer, vol. 72(3), pages 707-726, April.
    3. Tutz, Gerhard & Pößnecker, Wolfgang & Uhlmann, Lorenz, 2015. "Variable selection in general multinomial logit models," Computational Statistics & Data Analysis, Elsevier, vol. 82(C), pages 207-222.
    4. Steffen Borgwardt & Rafael M. Frongillo, 2019. "Power Diagram Detection with Applications to Information Elicitation," Journal of Optimization Theory and Applications, Springer, vol. 181(1), pages 184-196, April.
    5. Ye, Ya-Fen & Shao, Yuan-Hai & Deng, Nai-Yang & Li, Chun-Na & Hua, Xiang-Yu, 2017. "Robust Lp-norm least squares support vector regression with feature selection," Applied Mathematics and Computation, Elsevier, vol. 305(C), pages 32-52.
    6. Vincent, Martin & Hansen, Niels Richard, 2014. "Sparse group lasso and high dimensional multinomial classification," Computational Statistics & Data Analysis, Elsevier, vol. 71(C), pages 771-786.
    7. Abhik Ghosh & Magne Thoresen, 2018. "Non-concave penalization in linear mixed-effect models and regularized selection of fixed effects," AStA Advances in Statistical Analysis, Springer;German Statistical Society, vol. 102(2), pages 179-210, April.
    8. Steinwart, Ingo & Hush, Don & Scovel, Clint, 2009. "Learning from dependent observations," Journal of Multivariate Analysis, Elsevier, vol. 100(1), pages 175-194, January.
    9. Weiyang Ding & Michael K. Ng & Wenxing Zhang, 2024. "A generalized alternating direction implicit method for consensus optimization: application to distributed sparse logistic regression," Journal of Global Optimization, Springer, vol. 90(3), pages 727-753, November.
    10. Fang, Libing & Sun, Boyang & Li, Huijing & Yu, Honghai, 2018. "Systemic risk network of Chinese financial institutions," Emerging Markets Review, Elsevier, vol. 35(C), pages 190-206.
    11. Mohit Agrawal & Joseph G. Altonji & Richard K. Mansfield, 2019. "Quantifying Family, School, and Location Effects in the Presence of Complementarities and Sorting," Journal of Labor Economics, University of Chicago Press, vol. 37(S1), pages 11-83.
    12. Xiaotong Shen & Lifeng Wang, 2007. "Discussion of ``2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization'' by V. Koltchinskii," Papers 0708.0121, arXiv.org.
    13. Lee, Wonyul & Liu, Yufeng, 2012. "Simultaneous multiple response regression and inverse covariance matrix estimation via penalized Gaussian maximum likelihood," Journal of Multivariate Analysis, Elsevier, vol. 111(C), pages 241-255.
    14. Mohamed Ouhourane & Yi Yang & Andréa L. Benedet & Karim Oualkacha, 2022. "Group penalized quantile regression," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 31(3), pages 495-529, September.
    15. Croux, Christophe & Jagtiani, Julapa & Korivi, Tarunsai & Vulanovic, Milos, 2020. "Important factors determining Fintech loan default: Evidence from a lendingclub consumer platform," Journal of Economic Behavior & Organization, Elsevier, vol. 173(C), pages 270-296.
    16. Choi, Sungwoo & Park, Junyong, 2014. "Nonparametric additive model with grouped lasso and maximizing area under the ROC curve," Computational Statistics & Data Analysis, Elsevier, vol. 77(C), pages 313-325.
    17. Peter L. Bartlett & Shahar Mendelson, 2007. "Discussion of "2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization" by V. Koltchinskii," Papers 0708.0089, arXiv.org.
    18. Toru Kitagawa & Shosei Sakaguchi & Aleksey Tetenov, 2021. "Constrained Classification and Policy Learning," Papers 2106.12886, arXiv.org, revised Jul 2023.
    19. Xian Zhang & Dingtao Peng, 2022. "Solving constrained nonsmooth group sparse optimization via group Capped- $$\ell _1$$ ℓ 1 relaxation and group smoothing proximal gradient algorithm," Computational Optimization and Applications, Springer, vol. 83(3), pages 801-844, December.
    20. Hung Yi Lee & Charles Hernandez & Hongcheng Liu, 2023. "Regularized sample average approximation for high-dimensional stochastic optimization under low-rankness," Journal of Global Optimization, Springer, vol. 85(2), pages 257-282, February.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:crs:wpaper:2017-30. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Secretariat General (email available below). General contact details of provider: https://edirc.repec.org/data/crestfr.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.