On Convex Duality in Linear Inverse Problems
In this article we dwell into the class of so called ill posed Linear Inverse Problems (LIP) in machine learning, which has become almost a classic in recent times. The fundamental task in an LIP is to recover the entire signal / data from its relatively few random linear measurements. Such problems arise in variety of settings with applications ranging from medical image processing, recommender systems etc. We provide an exposition to the convex duality of the linear inverse problems, and obtain a novel and equivalent convex-concave min-max reformulation that gives rise to simple ascend-descent type algorithms to solve an LIP. Moreover, such a reformulation is crucial in developing methods to solve the dictionary learning problem with almost sure recovery constraints.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingDictionary LearningRecommendation SystemsSimilar Papers 제목 키워드 기반
Convex Regularization Behind Neural Reconstruction
Neural networks have shown tremendous potential for reconstructing high-resolution images in inverse problems. The non-convex and opaque nature of neural networks, however, hinders their utility in sensitive applications…
DenoisingGeometric Inference for General High-Dimensional Linear Inverse Problems
This paper presents a unified geometric framework for the statistical analysis of a general ill-posed linear inverse model which includes as special cases noisy compressed sensing, sign vector recovery, trace regression,…
compressed sensingMatrix CompletionregressionTwo-sample testing+1Functional Nonlinear Sparse Models
Signal processing is rich in inherently continuous and often nonlinear applications, such as spectral estimation, optical imaging, and super-resolution microscopy, in which sparsity plays a key role in obtaining state-of…
Robust classificationSpectrum CartographySuper-ResolutionParallel Deep Neural Networks Have Zero Duality Gap
Training deep neural networks is a challenging non-convex optimization problem. Recent work has proven that the strong duality holds (which means zero duality gap) for regularized finite-width two-layer ReLU networks and…
Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex
Several recently proposed architectures of neural networks such as ResNeXt, Inception, Xception, SqueezeNet and Wide ResNet are based on the designing idea of having multiple branches and have demonstrated improved perfo…