# Optimal Learning from Label Proportions with General Loss Functions

arXiv: https://arxiv.org/abs/2509.15145 · HTML: https://mlsanity.com/paper/2509.15145/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 51 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [Mean estimation and regression under heavy-tailed distributions--a survey](https://mlsanity.com/paper/1906.04280/) (2019)
- [On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data](https://mlsanity.com/paper/1808.10585/) (2018)
- [Deep multi-class learning from label proportions](https://mlsanity.com/paper/1905.12909/) (2019)
- [Learning from Label Proportions by Learning with Label Noise](https://mlsanity.com/paper/2203.02496/) (2022)
- [Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayes](https://mlsanity.com/paper/1605.00252/) (2016)
- [Learning from Label Proportions with Generative Adversarial Networks](https://mlsanity.com/paper/1909.02180/) (2019)
- [Weakly Supervised Classification in High Energy Physics](https://mlsanity.com/paper/1702.00414/) (2017)
- [Easy Learning from Label Proportions](https://mlsanity.com/paper/2302.03115/) (2023)
- [Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification](https://mlsanity.com/paper/2102.00678/) (2021)
- [PAC Learning Linear Thresholds from Label Proportions](https://mlsanity.com/paper/2310.10098/) (2023)
- [Optimistic Rates for Learning from Label Proportions](https://mlsanity.com/paper/2406.00487/) (2024)
- [Nearly Optimal Sample Complexity for Learning with Label Proportions](https://mlsanity.com/paper/2505.05355/) (2025)
- [Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means](https://mlsanity.com/paper/2506.14673/) (2025)

## Built on by (most cited first, 1 of 1)

- [Statistical Learning from Attribution Sets](https://mlsanity.com/paper/2602.06276/) (2026)

## Abstract (arXiv)

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.