Minimization of Transformed Penalty: Closed Form Representation and Iterative Thresholding Algorithms
arXiv:1412.5240
Abstract
The transformed penalty (TL1) functions are a one parameter family of bilinear transformations composed with the absolute value function. When acting on vectors, the TL1 penalty interpolates and similar to norm (). In our companion paper, we showed that TL1 is a robust sparsity promoting penalty in compressed sensing (CS) problems for a broad range of incoherent and coherent sensing matrices. Here we develop an explicit fixed point representation for the TL1 regularized minimization problem. The TL1 thresholding functions are in closed form for all parameter values. In contrast, the thresholding functions () are in closed form only for , known as hard, soft, half, and 2/3 thresholding respectively. The TL1 threshold values differ in subcritical (supercritical) parameter regime where the TL1 threshold functions are continuous (discontinuous) similar to soft-thresholding (half-thresholding) functions. We propose TL1 iterative thresholding algorithms and compare them with hard and half thresholding algorithms in CS test problems. For both incoherent and coherent sensing matrices, a proposed TL1 iterative thresholding algorithm with adaptive subcritical and supercritical thresholds consistently performs the best in sparse signal recovery with and without measurement noise.
References in corpus (4)
- Nearly unbiased variable selection under minimax concave penalty
- Regularization: Convergence of Iterative Half Thresholding Algorithm
- Minimization of Transformed Penalty: Theory, Difference of Convex Function Algorithm, and Robust Application in Compressed Sensing
- Transformed Schatten-1 Iterative Thresholding Algorithms for Low Rank Matrix Completion