no code implementations • 20 Feb 2024 • Carter Lyons, Raghu G. Raj, Margaret Cheney
In this paper, we develop novel generalization error bounds for a class of unrolled DNNs that are informed by a compound Gaussian prior.
1 code implementation • 28 Nov 2023 • Carter Lyons, Raghu G. Raj, Margaret Cheney
Incorporating prior information into inverse problems, e. g. via maximum-a-posteriori estimation, is an important technique for facilitating robust inverse problem solutions.
1 code implementation • IEEE Transactions on Signal Processing 2023 • Carter Lyons, Raghu G. Raj, Margaret Cheney
The first approach is an iterative algorithm that minimizes a regularized least squares objective function where the regularization is based on a compound Gaussian prior distribution.