Analytic and Bootstrap-after-Cross-Validation Methods for Selecting Penalty Parameters of High-Dimensional M-Estimators
Publikation: Working paper › Forskning
Dokumenter
- 2104
Forlagets udgivne version, 990 KB, PDF-dokument
We develop two new methods for selecting the penalty parameter for the $\ell^1$-penalized high-dimensional M-estimator, which we refer to as the analytic and bootstrap-after-cross-validation methods. For both methods, we derive nonasymptotic error bounds for the corresponding $\ell^1$-penalized M-estimator and show that the bounds converge to zero under mild conditions, thus providing a theoretical justification for these methods. We demonstrate via simulations that the finite-sample performance of our methods is much better than that of previously available and theoretically justified methods.
Originalsprog | Engelsk |
---|---|
Antal sider | 63 |
Status | Udgivet - 10 apr. 2021 |
Navn | University of Copenhagen. Institute of Economics. Discussion Papers (Online) |
---|---|
Nummer | 04 |
Vol/bind | 21 |
ISSN | 1601-2461 |
- Det Samfundsvidenskabelige Fakultet
Forskningsområder
Links
- https://arxiv.org/abs/2104.04716
Forlagets udgivne version
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 288855332