Saved in:
Bibliographic Details
Main Authors: Applebaum, Lorne, Dick, Travis, Gentile, Claudio, Kaplan, Haim, Koren, Tomer
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.15145
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Motivated by problems in online advertising, we address the task of Learning from Label Proportions (LLP). We introduce a novel and versatile low-variance debiasing methodology to learn from aggregate label information, significantly advancing the state of the art in LLP. Our debiasing approach exhibits remarkable flexibility, seamlessly accommodating a broad spectrum of practically relevant loss functions across both binary and multi-class classification settings. By carefully combining our estimators with standard techniques, we improve sample complexity guarantees for a large class of losses of practical relevance. We also empirically validate the efficacy of our proposed approach across a diverse array of benchmark datasets, demonstrating compelling empirical advantages over standard baselines.