Prediction bounds for higher order total variation regularized least squares

DOI10.1214/21-AOS2054zbMath1486.62205arXiv1904.10871OpenAlexW3213310890MaRDI QIDQ2054527

Francesco Ortelli, Sara van de Geer

Publication date: 3 December 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1904.10871

zbMATH Keywords

minimaxprojectionanalysiscompatibilityoracle inequalitytotal variation regularizationMoore-Penrose pseudo inverse

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Ridge regression; shrinkage estimators (Lasso) (62J07) Linear regression; mixed models (62J05) Linear inference, regression (62J99)

Related Items

The Lasso with structured design and entropy of (absolute) convex hulls, A cross-validation framework for signal denoising with applications to trend filtering, dyadic CART and beyond, Tensor denoising with trend filtering

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• On the prediction performance of the Lasso
• Splines in higher order TV regularization
• Locally adaptive regression splines
• On stepwise pattern recovery of the fused Lasso
• Minimax estimation via wavelet shrinkage
• Adaptive estimation of a quadratic functional by model selection.
• Adaptive risk bounds in univariate total variation denoising and trend filtering
• Additive models with trend filtering
• Adaptive piecewise polynomial estimation via trend filtering
• Near Minimax Line Spectral Estimation
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• $\ell_1$ Trend Filtering
• Adapting to unknown noise level in sparse deconvolution
• Logistic regression with total variation regularization
• Oracle inequalities for square root analysis estimators with application to total variation penalties
• A Probabilistic and RIPless Theory of Compressed Sensing
• Analysis versus synthesis in signal priors
• Towards a Mathematical Theory of Super‐resolution