Sökning: WFRF:(Panahi Ashkan 1986) >
Double Descent in F...
Double Descent in Feature Selection: Revisiting LASSO and Basis Pursuit
-
- Bosch, David, 1997 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Panahi, Ashkan, 1986 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Ozcelikkale, Ayca, 1982 (författare)
- Uppsala universitet,Signaler och system,Uppsala University
-
(creator_code:org_t)
- 2021
- 2021
- Engelska.
-
Ingår i: Thirty-eighth International Conference on Machine Learning, ICML 2021.
- Relaterad länk:
-
https://drive.google...
-
visa fler...
-
https://icml.cc/Conf...
-
https://research.cha...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- We present a novel analysis of feature selection in linear models by the convex framework of least absolute shrinkage operator (LASSO) and basis pursuit (BP). Our analysis pertains to a general overparametrized scenario. When the numbers of the features and the data samples grow proportionally, we obtain precise expressions for the asymptotic generalization error of LASSO and BP. Considering a mixture of strong and weak features, we provide insights into regularization trade-offs for double descent for l1 norm minimization. We validate these results with numerical experiments.
Ämnesord
- NATURVETENSKAP -- Matematik -- Beräkningsmatematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Computational Mathematics (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Overparameterization
- LASSO
- CGMT
- Basis Pursuit
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)