Solving Inverse Problems with Model Mismatch using Untrained Neural Networks within Model-based Architectures

arXiv:2403.04847v1 Announce Type: new
Abstract: Model-based deep learning methods such as \emph{loop unrolling} (LU) and \emph{deep equilibrium model} (DEQ) extensions offer outstanding performance in solving inverse problems (IP). These methods unroll the optimization iterations into a sequence of neural networks that in effect learn a regularization function from data. While these architectures are currently state-of-the-art in numerous applications, their success heavily relies on the accuracy of the forward model. This assumption can be limiting in many physical applications due to …

abstract architectures arxiv cs.lg deep learning eess.sp equilibrium extensions function learn loop networks neural networks optimization performance regularization type