DMCA
Adaptive forward-backward greedy algorithm for learning sparse representations (2011)
Cached
Download Links
| Venue: | IEEE Trans. Inform. Theory |
| Citations: | 101 - 9 self |
BibTeX
@ARTICLE{Zhang11adaptiveforward-backward,
author = {Tong Zhang},
title = {Adaptive forward-backward greedy algorithm for learning sparse representations},
journal = {IEEE Trans. Inform. Theory},
year = {2011}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Consider linear prediction models where the target function is a sparse linear combination of a set of basis functions. We are interested in the problem of identifying those basis functions with non-zero coefficients and reconstructing the target function from noisy observations. Two heuristics that are widely used in practice are forward and backward greedy algorithms. First, we show that neither idea is adequate. Second, we propose a novel combination that is based on the forward greedy algorithm but takes backward steps adaptively whenever beneficial. We prove strong theoretical results showing that this procedure is effective in learning sparse representations. Experimental results support our theory. 1
Keyphrases
sparse representation adaptive forward-backward greedy algorithm target function basis function non-zero coefficient novel combination sparse linear combination backward step strong theoretical result noisy observation linear prediction model greedy algorithm forward greedy algorithm experimental result
