Abstract | ||
---|---|---|
We revisit the positive cone condition given by Efron for the over-determined least absolute shrinkage and selection operator (LASSO). It is a sufficient condition ensuring that the number of nonzero entries in the solution vector keeps increasing when the penalty parameter decreases, based on which the least angle regression (LARS) and homotopy algorithms yield the same iterates. We show that the... |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/LSP.2012.2221712 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Coherence,Vectors,Signal processing algorithms,Optimization | Mathematical optimization,Combinatorics,Sparse approximation,Lasso (statistics),Diagonally dominant matrix,Homotopy,Gramian matrix,Least-angle regression,Iterated function,Mutual coherence,Mathematics | Journal |
Volume | Issue | ISSN |
19 | 12 | 1070-9908 |
Citations | PageRank | References |
3 | 0.41 | 2 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Junbo Duan | 1 | 23 | 4.65 |
Charles Soussen | 2 | 113 | 15.21 |
David Brie | 3 | 130 | 24.28 |
Idier, J. | 4 | 566 | 59.01 |
Yu-Ping Wang | 5 | 281 | 58.87 |