Adaptive risk bounds in univariate total variation denoising and trend filtering
Authors:
- Adityanand GuntuboyinaAGAdityanand Guntuboyina
- Donovan LieuDLDonovan Lieu
- Sabyasachi ChatterjeeSCSabyasachi Chatterjee
- Bodhisattva SenBSBodhisattva Sen
- 1 February 2020
- journal article
- research article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 48 (1) , 205-229
Abstract
We study trend filtering, a relatively recent method for univariate nonparametric regression. For a given integer $r\geq1$, the $r$th order trend filtering estimator is defined as the minimizer of the sum of squared errors when we constrain (or penalize) the sum of the absolute $r$th order discrete derivatives of the fitted function at the design points. For $r=1$, the estimator reduces to total variation regularization which has received much attention in the statistics and image processing literature. In this paper, we study the performance of the trend filtering estimator for every $r\geq1$, both in the constrained and penalized forms. Our main results show that in the strong sparsity setting when the underlying function is a (discrete) spline with few “knots,” the risk (under the global squared error loss) of the trend filtering estimator (with an appropriate choice of the tuning parameter) achieves the parametric $n^{-1}$-rate, up to a logarithmic (multiplicative) factor. Our results therefore provide support for the use of trend filtering, for every $r\geq1$, in the strong sparsity setting.
Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Multiple Change-Point Estimation With a Total Variation PenaltyJournal of the American Statistical Association, 2010
- Combinatorics of random processes and sections of convex bodiesAnnals of Mathematics, 2006
- Spatially adaptive smoothing splinesBiometrika, 2006
- Smoothers for Discontinuous SignalsJournal of Nonparametric Statistics, 2002
- Minimax estimation via wavelet shrinkageThe Annals of Statistics, 1998
- Optimal spatial adaptation to inhomogeneous smoothness: an approach based on kernel estimates with variable bandwidth selectorsThe Annals of Statistics, 1997
- Locally adaptive regression splinesThe Annals of Statistics, 1997
- Locally Adaptive Bandwidth Choice for Kernel Regression EstimatorsJournal of the American Statistical Association, 1993
- Multivariate Adaptive Regression SplinesThe Annals of Statistics, 1991
- Variable Bandwidth Kernel Estimators of Regression CurvesThe Annals of Statistics, 1987