A new algorithm for computing sparse solutions to linear inverse problems

We present an iterative algorithm for computing sparse solutions (or sparse approximate solutions) to linear inverse problems. The algorithm is intended to supplement the existing arsenal of techniques. It is shown to converge to the local minima of a function of the form used for picking out sparse solutions, and its connection with existing techniques explained. Finally, it is demonstrated on subset selection and deconvolution examples. The fact that the proposed algorithm is sometimes successful when existing greedy algorithms fail is also demonstrated.

[1]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[2]  Bhaskar D. Rao,et al.  A recursive weighted minimum norm algorithm: Analysis and applications , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Jean-Jacques Fuchs.  Extension of the Pisarenko method to sparse linear arrays , 1997, IEEE Trans. Signal Process..

[4]  Anthony N. Sinclair,et al.  Recovery of a sparse spike time series by L1 norm deconvolution , 1994, IEEE Trans. Signal Process..

[5]  Bhaskar D. Rao,et al.  Convergence analysis of a class of adaptive weighted norm extrapolation algorithms , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[6]  Yoram Bresler,et al.  Efficient edge-preserving regularization for limited-angle tomography , 1995, Proceedings., International Conference on Image Processing.

[7]  Michel Barlaud,et al.  An adaptive reconstruction method involving discontinuities , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  R. Gallager.  Information Theory and Reliable Communication , 1968 .

[9]  Balas K. Natarajan,et al.  Sparse Approximate Solutions to Linear Systems , 1995, SIAM J. Comput..

[10]  Gene H. Golub,et al.  Matrix computations , 1983 .