Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Learning from positive and unlabeled examples -Finite size sample bounds
Authors: Farnam Mansouri, Shai Ben-David
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper provides a theoretical analysis of the statistical complexity of PU learning under a wider range of setups. Unlike most prior work, our study does not assume that the class prior is known to the learner. We prove upper and lower bounds on the required sample sizes (of both the positively labeled and the unlabeled samples). |
| Researcher Affiliation | Academia | Farnam Mansouri University of Waterloo and Vector Institute EMAIL Shai Ben-David University of Waterloo and Vector Institute EMAIL |
| Pseudocode | Yes | Algorithm 1: Algorithm for PU learning in the positive covariate shift setup |
| Open Source Code | No | This is a purely theoretical paper, without experiments. |
| Open Datasets | No | This is a purely theoretical paper, without experiments. |
| Dataset Splits | No | This is a purely theoretical paper, without experiments. |
| Hardware Specification | No | This is a purely theoretical paper, without experiments. |
| Software Dependencies | No | This is a purely theoretical paper, without experiments. |
| Experiment Setup | No | This is a purely theoretical paper, without experiments. |