On the Lagrangian biduality of sparsity minimization problems
Files
First author draft
Date
2012-01-01
DOI
Authors
Singaraju, Dheeraj
Tron, Roberto
Elhamifar, Ehsan
Yang, Allen Y.
Sastry, S. Shankar
Version
OA Version
Citation
Dheeraj Singaraju, Roberto Tron, Ehsan Elhamifar, Allen Y Yang, S Shankar Sastry. 2012. "On the Lagrangian Biduality of Sparsity Minimization Problems." 2012 IEEE International Conference On Acoustics, Speech And Signal Processing (ICASSP), pp. 3429 - 3432 (4).
Abstract
Recent results in Compressive Sensing have shown that, under certain conditions, the solution to an underdetermined system of linear equations with sparsity-based regularization can be accurately recovered by solving convex relaxations of the original problem. In this work, we present a novel primal-dual analysis on a class of sparsity minimization problems. We show that the Lagrangian bidual (i.e., the Lagrangian dual of the Lagrangian dual) of the sparsity minimization problems can be used to derive interesting convex relaxations: the bidual of the ℓ0-minimization problem is the ℓ1-minimization problem; and the bidual of the ℓ0,1-minimization problem for enforcing group sparsity on structured data is the ℓ1,∞-minimization problem. The analysis provides a means to compute per-instance non-trivial lower bounds on the (group) sparsity of the desired solutions. In a real-world application, the bidual relaxation improves the performance of a sparsity-based classification framework applied to robust face recognition.