Skip to Main content Skip to Navigation
Journal articles

Learning Co-Sparse Analysis Operators with Separable Structures

Abstract : In the co-sparse analysis model a set of filters is applied to a signal out of the signal class of interest yielding sparse signal responses. As such, it may serve as a prior in inverse problems, or for structural analysis of signals that are known to belong to the signal class. The more the model is adapted to the class, the more reliable it is for these purposes. The task of learning such operators for a given class is therefore a crucial problem. In many applications, it is also required that the filter responses are obtained in a timely manner, which can be achieved by filters with a separable structure. Not only can operators of this sort be efficiently used for computing the filter responses, but they also have the advantage that less training samples are required to obtain a reliable estimate of the operator. The first contribution of this work is to give theoretical evidence for this claim by providing an upper bound for the sample complexity of the learning process. The second is a stochastic gradient descent (SGD) method designed to efficiently learn an analysis operators with separable structures, which incorporates an efficient step size selection. Numerical experiments are provided that link the sample complexity to the convergence speed of the SGD algorithm.
Complete list of metadata

Cited literature [39 references]  Display  Hide  Download
Contributor : Rémi Gribonval <>
Submitted on : Monday, October 5, 2015 - 9:00:04 PM
Last modification on : Friday, January 8, 2021 - 3:39:50 AM
Long-term archiving on: : Wednesday, April 26, 2017 - 10:27:37 PM


Files produced by the author(s)



Matthias Seibert, Julian Wörmann, Rémi Gribonval, Martin Kleinsteuber. Learning Co-Sparse Analysis Operators with Separable Structures. IEEE Transactions on Signal Processing, Institute of Electrical and Electronics Engineers, 2015, 64 (1), pp.120-130. ⟨10.1109/TSP.2015.2481875⟩. ⟨hal-01130411⟩



Record views


Files downloads