Iterative regularization for convex regularizers
We study iterative regularization for linear models, when the bias is convex but not necessarily strongly convex. We characterize the stability properties of a primal-dual gradient based approach, analyzing its convergence in the presence of worst case deterministic noise. As a main example, we specialize and illustrate the results for the problem of robust sparse recovery. Key to our analysis is a combination of ideas from regularization theory and optimization in the presence of errors. Theoretical results are complemented by experiments showing that state-of-the-art performances can be achieved with considerable computational speed-ups.
Code (1)
Similar Papers 제목 키워드 기반
Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms
We propose to learn non-convex regularizers with a prescribed upper bound on their weak-convexity modulus. Such regularizers give rise to variational denoisers that minimize a convex energy. They rely on few parameters (…
Image ReconstructionMRI ReconstructionIterative regularization for low complexity regularizers
Iterative regularization exploits the implicit bias of an optimization algorithm to regularize ill-posed problems. Constructing algorithms with such built-in regularization mechanisms is a classic challenge in inverse pr…
Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
This paper develops a new class of nonconvex regularizers for low-rank matrix recovery. Many regularizers are motivated as convex relaxations of the matrix rank function. Our new factor group-sparse regularizers are moti…
Low-Rank Matrix CompletionMatrix CompletionTensor-based formulation and nuclear norm regularization for multi-energy computed tomography
The development of energy selective, photon counting X-ray detectors allows for a wide range of new possibilities in the area of computed tomographic image formation. Under the assumption of perfect energy resolution, he…
Computed Tomography (CT)Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraints
Regularization is a central tool for addressing ill-posedness in inverse problems and statistical estimation, with the choice of a suitable penalty often determining the reliability and interpretability of downstream sol…