Acquisition compriméeL'acquisition comprimée (en anglais compressed sensing) est une technique permettant de trouver la solution la plus parcimonieuse d'un système linéaire sous-déterminé. Elle englobe non seulement les moyens pour trouver cette solution mais aussi les systèmes linéaires qui sont admissibles. En anglais, elle porte le nom de Compressive sensing, Compressed Sampling ou Sparse Sampling.
Sparse approximationSparse approximation (also known as sparse representation) theory deals with sparse solutions for systems of linear equations. Techniques for finding these solutions and exploiting them in applications have found wide use in , signal processing, machine learning, medical imaging, and more. Consider a linear system of equations , where is an underdetermined matrix and . The matrix (typically assumed to be full-rank) is referred to as the dictionary, and is a signal of interest.
Sparse dictionary learningSparse dictionary learning (also known as sparse coding or SDL) is a representation learning method which aims at finding a sparse representation of the input data in the form of a linear combination of basic elements as well as those basic elements themselves. These elements are called atoms and they compose a dictionary. Atoms in the dictionary are not required to be orthogonal, and they may be an over-complete spanning set. This problem setup also allows the dimensionality of the signals being represented to be higher than the one of the signals being observed.
Stochastic optimizationStochastic optimization (SO) methods are optimization methods that generate and use random variables. For stochastic problems, the random variables appear in the formulation of the optimization problem itself, which involves random objective functions or random constraints. Stochastic optimization methods also include methods with random iterates. Some stochastic optimization methods use random iterates to solve stochastic problems, combining both meanings of stochastic optimization.
Algorithme du gradientLalgorithme du gradient, aussi appelé algorithme de descente de gradient, désigne un algorithme d'optimisation différentiable. Il est par conséquent destiné à minimiser une fonction réelle différentiable définie sur un espace euclidien (par exemple, , l'espace des n-uplets de nombres réels, muni d'un produit scalaire) ou, plus généralement, sur un espace hilbertien. L'algorithme est itératif et procède donc par améliorations successives. Au point courant, un déplacement est effectué dans la direction opposée au gradient, de manière à faire décroître la fonction.