Frank-Wolfe Algorithm for the Exact Sparse Problem

12/18/2018
by   Farah Cherfaoui, et al.
0

In this paper, we study the properties of the Frank-Wolfe algorithm to solve the reconstruction problem. We prove that when the dictionary is quasi-incoherent, at each iteration, the Frank-Wolfe algorithm picks up an atom indexed by the support. We also prove that when the dictionary is quasi-incoherent, there exists an iteration beyond which the algorithm converges exponentially fast.

READ FULL TEXT

page 1

page 2

page 3

research
06/06/2019

Complete Dictionary Learning via ℓ^4-Norm Maximization over the Orthogonal Group

This paper considers the fundamental problem of learning a complete (ort...
research
09/07/2018

Fast greedy algorithms for dictionary selection with generalized sparsity constraints

In dictionary selection, several atoms are selected from finite candidat...
research
10/06/2020

Towards an arboretum of monadically stable classes of graphs

Logical transductions provide a very useful tool to encode classes of st...
research
09/03/2020

On a non-archimedean broyden method

Newton's method is an ubiquitous tool to solve equations, both in the ar...
research
02/28/2012

Fast approximations to structured sparse coding and applications to object classification

We describe a method for fast approximation of sparse coding. The input ...
research
03/13/2023

A collection of memos dedicated to exact base-21 (EBTO) and quasi base-21 (QBTO) codes

This collection bundles the following memos dedicated to the so called e...
research
06/29/2021

Convolutional Sparse Coding Fast Approximation with Application to Seismic Reflectivity Estimation

In sparse coding, we attempt to extract features of input vectors, assum...

Please sign up or login with your details

Forgot password? Click here to reset