# A scalable estimator of sets of integral operators

arXiv: https://arxiv.org/abs/1811.12192 · HTML: https://mlsanity.com/paper/1811.12192/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 1 of 1)

- [Image reconstruction in light-sheet microscopy: spatially varying deconvolution and mixed noise](https://mlsanity.com/paper/2108.03642/) (2021)

## Abstract (arXiv)

We propose a scalable method to find a subspace widehatH of low-rank tensors that simultaneously approximates a set of integral operators. The method can be seen as a generalization of the Tucker-2 decomposition model, which was never used in this context. In addition, we propose to construct a convex set widehatC subset widehatH as the convex hull of the observed operators. It is a minimax optimal estimator under the Nikodym metric. We then provide an efficient algorithm to compute projection on widehatC. We observe a good empirical behavior of the method in simulations. The main aim of this work is to improve the identifiability of complex linear operators in blind inverse problems.