Current browse context:
stat.ML
Change to browse by:
References & Citations
Statistics > Machine Learning
Title: Automated Model Selection for Generalized Linear Models
(Submitted on 25 Apr 2024)
Abstract: In this paper, we show how mixed-integer conic optimization can be used to combine feature subset selection with holistic generalized linear models to fully automate the model selection process. Concretely, we directly optimize for the Akaike and Bayesian information criteria while imposing constraints designed to deal with multicollinearity in the feature selection task. Specifically, we propose a novel pairwise correlation constraint that combines the sign coherence constraint with ideas from classical statistical models like Ridge regression and the OSCAR model.
Submission history
From: Benjamin Schwendinger [view email][v1] Thu, 25 Apr 2024 12:16:58 GMT (23kb)
Link back to: arXiv, form interface, contact.