Sensing Theorems for Unsupervised Learning in Linear Inverse Problems

Julián Tachella, Dongdong Chen, Michael E. Davies

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Solving an ill-posed linear inverse problem requires knowledge about the underlying signal model. In many applications, this model is a priori unknown and has to be learned from data. However, it is impossible to learn the model using observations obtained via a single incomplete measurement operator, as there is no information about the signal model in the nullspace of the operator, resulting in a chicken-and-egg problem: to learn the model we need reconstructed signals, but to reconstruct the signals we need to know the model. Two ways to overcome this limitation are using multiple measurement operators or assuming that the signal model is invariant to a certain group action. In this paper, we present necessary and sufficient sensing conditions for learning the signal model from measurement data alone which only depend on the dimension of the model and the number of operators or properties of the group action that the model is invariant to. As our results are agnostic of the learning algorithm, they shed light into the fundamental limitations of learning from incomplete data and have implications in a wide range set of practical algorithms, such as
dictionary learning, matrix completion and deep neural networks.
Original languageEnglish
Number of pages45
JournalJournal of Machine Learning Research
Volume24
Early online date23 Jan 2023
Publication statusE-pub ahead of print - 23 Jan 2023

Fingerprint

Dive into the research topics of 'Sensing Theorems for Unsupervised Learning in Linear Inverse Problems'. Together they form a unique fingerprint.

Cite this