Feature-weighted elastic net : using "features of features" for better prediction
In some supervised learning settings, the practitioner might have additional information on the features used for prediction. We propose a new method which leverages this additional information for better prediction. The method, which we call the feature-weighted elastic net ("fwelnet"), uses these "features of features" to adapt the relative penalties on the feature coefficients in the elastic net penalty. In our simulations, fwelnet outperforms the lasso in terms of test mean squared error and usually gives an improvement in true positive rate or false positive rate for feature selection. We also apply this method to early prediction of preeclampsia, where fwelnet outperforms the lasso in terms of 10-fold cross-validated area under the curve (0.86 vs. 0.80). We also provide a connection between fwelnet and the group lasso and suggest how fwelnet might be used for multi-task learning.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:33 |
---|---|
Enthalten in: |
Statistica Sinica - 33(2023), 1 vom: 17. Jan., Seite 259-279 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Tay, J Kenneth [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 10.05.2023 published: Print Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.5705/ss.202020.0226 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM356056872 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM356056872 | ||
003 | DE-627 | ||
005 | 20231226065641.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.5705/ss.202020.0226 |2 doi | |
028 | 5 | 2 | |a pubmed24n1186.xml |
035 | |a (DE-627)NLM356056872 | ||
035 | |a (NLM)37102071 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Tay, J Kenneth |e verfasserin |4 aut | |
245 | 1 | 0 | |a Feature-weighted elastic net |b using "features of features" for better prediction |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 10.05.2023 | ||
500 | |a published: Print | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a In some supervised learning settings, the practitioner might have additional information on the features used for prediction. We propose a new method which leverages this additional information for better prediction. The method, which we call the feature-weighted elastic net ("fwelnet"), uses these "features of features" to adapt the relative penalties on the feature coefficients in the elastic net penalty. In our simulations, fwelnet outperforms the lasso in terms of test mean squared error and usually gives an improvement in true positive rate or false positive rate for feature selection. We also apply this method to early prediction of preeclampsia, where fwelnet outperforms the lasso in terms of 10-fold cross-validated area under the curve (0.86 vs. 0.80). We also provide a connection between fwelnet and the group lasso and suggest how fwelnet might be used for multi-task learning | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Aghaeepour, Nima |e verfasserin |4 aut | |
700 | 1 | |a Hastie, Trevor |e verfasserin |4 aut | |
700 | 1 | |a Tibshirani, Robert |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Statistica Sinica |d 2003 |g 33(2023), 1 vom: 17. Jan., Seite 259-279 |w (DE-627)NLM184578523 |x 1017-0405 |7 nnns |
773 | 1 | 8 | |g volume:33 |g year:2023 |g number:1 |g day:17 |g month:01 |g pages:259-279 |
856 | 4 | 0 | |u http://dx.doi.org/10.5705/ss.202020.0226 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 33 |j 2023 |e 1 |b 17 |c 01 |h 259-279 |