Can I read Signal Recovery with Proximal Comixtures on EtoBox?

Signal Recovery with Proximal Comixtures by Combettes, Patrick L.; Cornejo, Diego J. is a scholarly article available to read on EtoBox.

What is Signal Recovery with Proximal Comixtures about?

In variational signal processing and machine learning problems, loss functions and linear operators are typically aggregated as an average of composite terms. We propose an alternative formulation using proximal comixtures, an operation that combines functions and linear operators in such a way that the proximity operator of the resulting function is computable explicitly. The benefits of comixture formulations are illustrated through image recovery and machine learning applications.

Author

Combettes, Patrick L.; Cornejo, Diego J.

Published

2024

Language

EN