Enregistré dans:
Détails bibliographiques
Auteurs principaux: van Cutsem, Maxime, Sardy, Sylvain
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.19374
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918165547581440
author van Cutsem, Maxime
Sardy, Sylvain
author_facet van Cutsem, Maxime
Sardy, Sylvain
contents We revisit Cox's proportional hazard models and LASSO in the aim of improving feature selection in survival analysis. Unlike traditional methods relying on cross-validation or BIC, the penalty parameter $λ$ is directly tuned for feature selection and is asymptotically pivotal thanks to taking the square root of Cox's partial likelihood. Substantially improving over both cross-validation LASSO and BIC subset selection, our approach has a phase transition on the probability of retrieving all and only the good features, like in compressed sensing. The method can be employed by linear models but also by artificial neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Square root Cox's survival analysis by the fittest linear and neural networks model
van Cutsem, Maxime
Sardy, Sylvain
Machine Learning
We revisit Cox's proportional hazard models and LASSO in the aim of improving feature selection in survival analysis. Unlike traditional methods relying on cross-validation or BIC, the penalty parameter $λ$ is directly tuned for feature selection and is asymptotically pivotal thanks to taking the square root of Cox's partial likelihood. Substantially improving over both cross-validation LASSO and BIC subset selection, our approach has a phase transition on the probability of retrieving all and only the good features, like in compressed sensing. The method can be employed by linear models but also by artificial neural networks.
title Square root Cox's survival analysis by the fittest linear and neural networks model
topic Machine Learning
url https://arxiv.org/abs/2510.19374