Homomorphic Sensing

Manolis Tsakiris, Liangzu Peng
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:6335-6344, 2019.

Abstract

A recent line of research termed "unlabeled sensing" and "shuffled linear regression" has been exploring under great generality the recovery of signals from subsampled and permuted measurements; a challenging problem in diverse fields of data science and machine learning. In this paper we introduce an abstraction of this problem which we call "homomorphic sensing". Given a linear subspace and a finite set of linear transformations we develop an algebraic theory which establishes conditions guaranteeing that points in the subspace are uniquely determined from their homomorphic image under some transformation in the set. As a special case, we recover known conditions for unlabeled sensing, as well as new results and extensions. On the algorithmic level we exhibit two dynamic programming based algorithms, which to the best of our knowledge are the first working solutions for the unlabeled sensing problem for small dimensions. One of them, additionally based on branch-and-bound, when applied to image registration under affine transformations, performs on par with or outperforms state-of-the-art methods on benchmark datasets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v97-tsakiris19a, title = {Homomorphic Sensing}, author = {Tsakiris, Manolis and Peng, Liangzu}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {6335--6344}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/tsakiris19a/tsakiris19a.pdf}, url = {https://proceedings.mlr.press/v97/tsakiris19a.html}, abstract = {A recent line of research termed "unlabeled sensing" and "shuffled linear regression" has been exploring under great generality the recovery of signals from subsampled and permuted measurements; a challenging problem in diverse fields of data science and machine learning. In this paper we introduce an abstraction of this problem which we call "homomorphic sensing". Given a linear subspace and a finite set of linear transformations we develop an algebraic theory which establishes conditions guaranteeing that points in the subspace are uniquely determined from their homomorphic image under some transformation in the set. As a special case, we recover known conditions for unlabeled sensing, as well as new results and extensions. On the algorithmic level we exhibit two dynamic programming based algorithms, which to the best of our knowledge are the first working solutions for the unlabeled sensing problem for small dimensions. One of them, additionally based on branch-and-bound, when applied to image registration under affine transformations, performs on par with or outperforms state-of-the-art methods on benchmark datasets.} }
Endnote
%0 Conference Paper %T Homomorphic Sensing %A Manolis Tsakiris %A Liangzu Peng %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-tsakiris19a %I PMLR %P 6335--6344 %U https://proceedings.mlr.press/v97/tsakiris19a.html %V 97 %X A recent line of research termed "unlabeled sensing" and "shuffled linear regression" has been exploring under great generality the recovery of signals from subsampled and permuted measurements; a challenging problem in diverse fields of data science and machine learning. In this paper we introduce an abstraction of this problem which we call "homomorphic sensing". Given a linear subspace and a finite set of linear transformations we develop an algebraic theory which establishes conditions guaranteeing that points in the subspace are uniquely determined from their homomorphic image under some transformation in the set. As a special case, we recover known conditions for unlabeled sensing, as well as new results and extensions. On the algorithmic level we exhibit two dynamic programming based algorithms, which to the best of our knowledge are the first working solutions for the unlabeled sensing problem for small dimensions. One of them, additionally based on branch-and-bound, when applied to image registration under affine transformations, performs on par with or outperforms state-of-the-art methods on benchmark datasets.
APA
Tsakiris, M. & Peng, L.. (2019). Homomorphic Sensing. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:6335-6344 Available from https://proceedings.mlr.press/v97/tsakiris19a.html.

Related Material