Pyglmnet: Python implementation of elastic-net regularized generalized linear models
Mainak Jasa b, Titipat Achakulvisutc, Aid Idrizović, Daniel Ernesto Acunad e, Matthew D. Antalekf, Vinicius Marquese, Tommy Odlandg, Ravi Garga b f, Mayank Agrawalf h, Yu Umegakii j, Peter Foleyk, Hugo Fernandesk, Drew Harrisk, Beibin Lik l, Olivier Pietersl m n o, Scott Ottersonp q, Giovanni De Tonip r, Chris Rodgersr s, Eva L. Dyers t, Matti Hämäläinena b, Konrad Paul Kordingc, Pavan Ramkumarm t
- aHarvard Medical School
- bMassachusetts General Hospital
- cUniversity of Pennsylvania
- dUniversity of Syracuse
- eLoyola University
- fNorthwestern University
- gSonat Consulting
- hPrinceton University
- iNTT DATA Mathematical Systems Inc 10 605 11 Rockets of Awesome 12 Epoch Capital 13
- jNTT DATA Mathematical Systems Inc
- kResearch Institute for Agriculture , Fisheries and Food
- lUniversity of Washington
- mSystem1 Biosciences Inc
- nIDLab-AIRO -Ghent University -imec
- oResearch Institute for Agriculture, Fisheries
- pIDLab-AIRO -Ghent University -imec Clean Power Research
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Generalized linear models (GLMs) are well-established tools for regression and classification and are widely applied across the sciences, economics, business, and finance.Owing to their convex loss, they are easy and efficient to fit.Moreover, they are relatively easy to interpret because of their well-defined noise distributions and point-wise nonlinearities.Mathematically, a GLM is estimated as follows: min β0,β