Early stopping for statistical inverse problems via truncated SVD estimation

by   Gilles Blanchard, et al.
Universität Potsdam
Humboldt-Universität zu Berlin
Université Paris-Dauphine

We consider truncated SVD (or spectral cut-off, projection) estimators for a prototypical statistical inverse problem in dimension D. Since calculating the singular value decomposition (SVD) only for the largest singular values is much less costly than the full SVD, our aim is to select a data-driven truncation level m∈{1,...,D} only based on the knowledge of the first m singular values and vectors. We analyse in detail whether sequential early stopping rules of this type can preserve statistical optimality. Information-constrained lower bounds and matching upper bounds for a residual based stopping rule are provided, which give a clear picture in which situation optimal sequential adaptation is feasible. Finally, a hybrid two-step approach is proposed which allows for classical oracle inequalities while considerably reducing numerical complexity.


page 1

page 2

page 3

page 4


Smoothed residual stopping for statistical inverse problems via truncated SVD estimation

This work examines under what circumstances adaptivity for truncated SVD...

High Order Numerical Methods To Approximate The Singular Value Decomposition

In this paper, we present a class of high order methods to approximate t...

Flip-Flop Spectrum-Revealing QR Factorization and Its Applications on Singular Value Decomposition

We present Flip-Flop Spectrum-Revealing QR (Flip-Flop SRQR) factorizatio...

Projection techniques to update the truncated SVD of evolving matrices

This paper considers the problem of updating the rank-k truncated Singul...

SVD-DIP: Overcoming the Overfitting Problem in DIP-based CT Reconstruction

The deep image prior (DIP) is a well-established unsupervised deep learn...

A Parallel Distributed Algorithm for the Power SVD Method

In this work, we study how to implement a distributed algorithm for the ...

Please sign up or login with your details

Forgot password? Click here to reset