Sorry, you need to enable JavaScript to visit this website.

MAP-informed Unrolled Algorithms for Hyper-parameter Estimation

Citation Author(s):
Submitted by:
Caroline Chaux
Last updated:
17 November 2023 - 12:05pm
Document Type:
Presentation Slides
Document Year:
Caroline Chaux

Hyper-parameter tuning, and especially regularisation parameter estimation, is a challenging but essential task when solving inverse problems. The solution is obtained here through the minimization of a functional composed of a data fidelity term and a regularization term. Those terms are balanced through a (or several) regularisation parameter(s) whose estimation is made under an unrolled strategy together with the inverse problem solving. The resulting network is
trained while incorporating information on the model through Maximum a Posteriori estimation which drastically decreases the amount of data needed for the training and results in better estimation results. The performances are demonstrated in a deconvolution context where the regularisation is performed in the wavelet domain.

0 users have voted: