Une véritable approche $\ell_0$ pour l'apprentissage de dictionnaire
This provides a computationally feasible exact solution to a fundamental sparse representation problem in signal/image processing, though it appears incremental in optimization approach.
The paper tackles the NP-hard optimization problem of dictionary learning with exact ℓ₀-norm sparsity control by reformulating it as a Mixed-Integer Quadratic Program (MIQP) and solving it globally using existing software, achieving competitive results in image denoising compared to state-of-the-art methods.
Sparse representation learning has recently gained a great success in signal and image processing, thanks to recent advances in dictionary learning. To this end, the $\ell_0$-norm is often used to control the sparsity level. Nevertheless, optimization problems based on the $\ell_0$-norm are non-convex and NP-hard. For these reasons, relaxation techniques have been attracting much attention of researchers, by priorly targeting approximation solutions (e.g. $\ell_1$-norm, pursuit strategies). On the contrary, this paper considers the exact $\ell_0$-norm optimization problem and proves that it can be solved effectively, despite of its complexity. The proposed method reformulates the problem as a Mixed-Integer Quadratic Program (MIQP) and gets the global optimal solution by applying existing optimization software. Because the main difficulty of this approach is its computational time, two techniques are introduced that improve the computational speed. Finally, our method is applied to image denoising which shows its feasibility and relevance compared to the state-of-the-art.