Oracle inequalities for square root analysis estimators with application to total variation penalties

Abstract

Through the direct study of the analysis estimator we derive oracle inequalities with fast and slow rates by adapting the arguments involving projections by Dalalyan, Hebiri and Lederer (2017). We then extend the theory to the square root analysis estimator. Finally, we focus on (square root) total variation regularized estimators on graphs and obtain constant-friendly rates, which, up to log-terms, match previous results obtained by entropy calculations. We also obtain an oracle inequality for the (square root) total variation regularized estimator over the cycle graph.

References in corpus (12)

• Square-Root Lasso: Pivotal Recovery of Sparse Signals via Conic Programming
• The solution path of the generalized lasso
• The Cosparse Analysis Model and Algorithms
• On the Prediction Performance of the Lasso
• Optimal rates for total variation denoising
• Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers
• The DFS Fused Lasso: Linear-Time Denoising over General Graphs
• Adaptive Risk Bounds in Univariate Total Variation Denoising and Trend Filtering
• Synthesis and analysis in total variation regularization
• On the total variation regularized estimator over a class of tree graphs
• The Group Square-Root Lasso: Theoretical Properties and Fast Algorithms
• Prediction bounds for higher order total variation regularized least squares