Early stopping for statistical inverse problems via truncated SVD estimation [article]

Gilles Blanchard, Marc Hoffmann, Markus Reiß
2018 arXiv   pre-print
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
more » ... l 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.
arXiv:1710.07278v3 fatcat:t6cwhiwl5jbvppeojtkcdbxy5i