Penalized versus constrained generalized eigenvalue problems
Gaynanova, Irina, Booth, James, Wells, Martin T.
We investigate the difference between using an $\ell_1$ penalty versus an $\ell_1$ constraint in generalized eigenvalue problems, such as principal component analysis and discriminant analysis. Our main finding is that an $\ell_1$ penalty may fail to provide very sparse solutions; a severe disadvantage for variable selection that can be remedied by using an $\ell_1$ constraint. Our claims are supported both by empirical evidence and theoretical analysis. Finally, we illustrate the advantages of an $\ell_1$ constraint in the context of discriminant analysis and principal component analysis.
May-4-2015
- Country:
- North America > United States > New York (0.14)
- Genre:
- Research Report (0.50)
- Industry:
- Health & Medicine > Therapeutic Area > Oncology (0.75)