Sharp oracle inequalities for Least Squares estimators in shape restricted regression

The performance of Least Squares (LS) estimators is studied in isotonic, unimodal and convex regression. Our results have the form of sharp oracle inequalities that account for the model misspecification error. In isotonic and unimodal regression, the LS estimator achieves the nonparametric rate $n^{-2/3}$ as well as a parametric rate of order $k/n$ up to logarithmic factors, where $k$ is the number of constant pieces of the true parameter. In univariate convex regression, the LS estimator satisfies an adaptive risk bound of order $q/n$ up to logarithmic factors, where $q$ is the number of affine pieces of the true regression function. This adaptive risk bound holds for any design points. While Guntuboyina and Sen (2013) established that the nonparametric rate of convex regression is of order $n^{-4/5}$ for equispaced design points, we show that the nonparametric rate of convex regression can be as slow as $n^{-2/3}$ for some worst-case design points. This phenomenon can be explained as follows: Although convexity brings more structure than unimodality, for some worst-case design points this extra structure is uninformative and the nonparametric rates of unimodal regression and convex regression are both $n^{-2/3}$.

[1]  Mary C. Meyer,et al.  ON THE DEGREES OF FREEDOM IN SHAPE-RESTRICTED REGRESSION , 2000 .

[2]  Cun-Hui Zhang Risk bounds in isotonic regression , 2002 .

[3]  P. Bartlett,et al.  Local Rademacher complexities , 2005, math/0508275.

[4]  J. Wellner,et al.  Estimation of a k-monotone density: limit distribution theory and the Spline connection , 2005, math/0509081.

[5]  J. Wellner,et al.  Entropy estimate for high-dimensional monotonic functions , 2005, math/0512641.

[6]  P. Bartlett,et al.  Empirical minimization , 2006 .

[7]  V. Koltchinskii Local Rademacher complexities and oracle inequalities in risk minimization , 2006, 0708.0083.

[8]  Andrew R. Barron,et al.  Information Theory and Mixing Least-Squares Regressions , 2006, IEEE Transactions on Information Theory.

[9]  Jean-Yves Audibert No fast exponential deviation inequalities for the progressive mixture rule , 2007 .

[10]  Alexandre B. Tsybakov,et al.  Introduction to Nonparametric Estimation , 2008, Springer series in statistics.

[11]  P. Bickel,et al.  SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTOR , 2008, 0801.1095.

[12]  V. Koltchinskii,et al.  Nuclear norm penalization and optimal rates for noisy low rank matrix completion , 2010, 1011.6256.

[13]  Fadoua Balabdaoui,et al.  Estimation of a k‐monotone density: characterizations, consistency and minimax lower bounds , 2010, Statistica Neerlandica.

[14]  A. Tsybakov,et al.  Exponential Screening and optimal rates of sparse estimation , 2010, 1003.2654.

[15]  A. Dalalyan,et al.  Sharp Oracle Inequalities for Aggregation of Affine Estimators , 2011, 1104.3969.

[16]  Karthik Sridharan,et al.  Empirical Entropy, Minimax Regret and Minimax Risk , 2013, ArXiv.

[17]  Adityanand Guntuboyina,et al.  Global risk bounds and adaptation in univariate convex regression , 2013, 1305.1648.

[18]  Tong Zhang,et al.  Aggregation of Affine Estimators , 2013, ArXiv.

[19]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[20]  Joel A. Tropp,et al.  Living on the edge: phase transitions in convex programs with random data , 2013, 1303.6672.

[21]  Y. Plan,et al.  High-dimensional estimation with geometric constraints , 2014, 1404.3749.

[22]  A. Tsybakov Aggregation and minimax optimality in high-dimensional estimation , 2014 .

[23]  S. Chatterjee A new perspective on least squares under convex constraint , 2014, 1402.0830.

[24]  R. Vershynin Estimation in High Dimensions: A Geometric Perspective , 2014, 1405.5103.

[25]  Adityanand Guntuboyina,et al.  On risk bounds in isotonic and other shape restricted regression problems , 2013, 1311.3765.

[26]  Pierre C. Bellec,et al.  Sharp oracle bounds for monotone and convex regression through aggregation , 2015, J. Mach. Learn. Res..

[27]  Adityanand Guntuboyina,et al.  On matrix estimation under monotonicity constraints , 2015, 1506.03430.

[28]  Babak Hassibi,et al.  Asymptotically Exact Denoising in Relation to Compressed Sensing , 2013, ArXiv.

[29]  P. Rigollet,et al.  Optimal rates of statistical seriation , 2016, Bernoulli.

[30]  J. Lafferty,et al.  Adaptive risk bounds in unimodal regression , 2015, Bernoulli.