Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Jizhou, Juba, Brendan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.15592
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909797527322624
author Huang, Jizhou
Juba, Brendan
author_facet Huang, Jizhou
Juba, Brendan
contents In machine learning applications, predictive models are trained to serve future queries across the entire data distribution. Real-world data often demands excessively complex models to achieve competitive performance, however, sacrificing interpretability. Hence, the growing deployment of machine learning models in high-stakes applications, such as healthcare, motivates the search for methods for accurate and explainable predictions. This work proposes a Personalized Prediction scheme, where an easy-to-interpret predictor is learned per query. In particular, we wish to produce a "sparse linear" classifier with competitive performance specifically on some sub-population that includes the query point. The goal of this work is to study the PAC-learnability of this prediction model for sub-populations represented by "halfspaces" in a label-agnostic setting. We first give a distribution-specific PAC-learning algorithm for learning reference classes for personalized prediction. By leveraging both the reference-class learning algorithm and a list learner of sparse linear representations, we prove the first upper bound, $O(\mathrm{opt}^{1/4} )$, for personalized prediction with sparse linear classifiers and homogeneous halfspace subsets. We also evaluate our algorithms on a variety of standard benchmark data sets.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15592
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Personalized Prediction By Learning Halfspace Reference Classes Under Well-Behaved Distribution
Huang, Jizhou
Juba, Brendan
Machine Learning
In machine learning applications, predictive models are trained to serve future queries across the entire data distribution. Real-world data often demands excessively complex models to achieve competitive performance, however, sacrificing interpretability. Hence, the growing deployment of machine learning models in high-stakes applications, such as healthcare, motivates the search for methods for accurate and explainable predictions. This work proposes a Personalized Prediction scheme, where an easy-to-interpret predictor is learned per query. In particular, we wish to produce a "sparse linear" classifier with competitive performance specifically on some sub-population that includes the query point. The goal of this work is to study the PAC-learnability of this prediction model for sub-populations represented by "halfspaces" in a label-agnostic setting. We first give a distribution-specific PAC-learning algorithm for learning reference classes for personalized prediction. By leveraging both the reference-class learning algorithm and a list learner of sparse linear representations, we prove the first upper bound, $O(\mathrm{opt}^{1/4} )$, for personalized prediction with sparse linear classifiers and homogeneous halfspace subsets. We also evaluate our algorithms on a variety of standard benchmark data sets.
title Personalized Prediction By Learning Halfspace Reference Classes Under Well-Behaved Distribution
topic Machine Learning
url https://arxiv.org/abs/2509.15592