Learning regularization parameters of inverse problems via deep neural networks. (24th September 2021)

• Record Type: Journal Article
• Authors: Afkham, Babak Maboudi; Chung, Julianne; Chung, Matthias
• Is Part Of: Inverse problems. Volume 37:Number 10(2021)
• Publication Date: 2021-09-24
• Subjects: deep learning -- regularization -- deep neural networks -- optimal experimental design -- hyperparameter selection -- bilevel optimization; Inverse problems (Differential equations) -- Periodicals; 515.357
• DOI: 10.1088/1361-6420/ac245d
• Languages: English
• ISSNs: 0266-5611

Abstract

Abstract: In this work, we describe a new approach that uses deep neural networks (DNN) to obtain regularization parameters for solving inverse problems. We consider a supervised learning approach, where a network is trained to approximate the mapping from observation data to regularization parameters. Once the network is trained, regularization parameters for newly obtained data are computed by efficient forward propagation of the DNN. We show that a wide variety of regularization functionals, forward models, and noise models may be considered. The network-obtained regularization parameters can be computed more efficiently and may even lead to more accurate solutions compared to existing regularization parameter selection methods. We emphasize that the key advantage of using DNNs for learning regularization parameters, compared to previous works on learning via bilevel optimization or empirical Bayes risk minimization, is greater generalizability. That is, rather than computing one set of parameters that is optimal with respect to one particular design objective, DNN-computed regularization parameters are tailored to the specific features or properties of the newly observed data. Thus, our approach may better handle cases where the observation is not a close representation of the training set. Furthermore, we avoid the need for expensive and challenging bilevel optimization methods as utilized in other existing training approaches. Numerical results demonstrate that trained DNNs can predict regularization parameters faster and better than existing methods, hence resulting in more accurate solutions to inverse problems.