Abstract | ||
---|---|---|
We consider the problem of variable group selection for least squares regression, namely, that of selecting groups of variables for best regression performance, leveraging and adhering to a natural grouping structure within the explanatory variables. We show that this problem can be efficiently addressed by using a cer- tain greedy style algorithm. More precisely, we propose the Group Orthogonal Matching Pursuit algorithm (Group-OMP), which extends the standard OMP pro- cedure (also referred to as "forward greedy feature selection algorithm" for least squares regression) to perform stage-wise group variable selection. We prove that under certain conditions Group-OMP can identify the correct (groups of) vari- ables. We also provide an upperbound on the l1 norm of the difference between the estimated regression coefficients and the true coefficients. Experimental re- sults on simulated and real world datasets indicate that Group-OMP compares favorably to Group Lasso, OMP and Lasso, both in terms of variable selection and prediction accuracy. |
Year | Venue | DocType |
---|---|---|
2009 | NIPS | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aurelie C. Lozano | 1 | 145 | 20.21 |
Grzegorz Swirszcz | 2 | 61 | 8.62 |
Naoki Abe | 3 | 111 | 7.37 |