Title: On the Confluence of Deep Learning and Energy Minimization Methods for Inverse Problems
Abstract: Many practical applications require to infer a desired quantity from measurements that contain implicit information about them, commonly resulting in ill-posed inverse reconstruction problems. While classical approaches formulate their solution as the argument that minimizes a suitable cost function, recent works dominate image reconstruction benchmarks using deep learning. This talk discusses possible ways of combining ideas from energy minimization and deep learning, including algorithmic schemes that introduce learned regularity, networks that iteratively minimize a model based cost function, and techniques that aim at learning suitable regularizers. For the latter, I will highlight recent advances and future challenges in the design of such parameterized regularizers as well as the solution of the bi-level optimization problems resulting from their training.