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..
Marginal-Nonuniform PAC Learnability
Authors: Steve Hanneke, Shay Moran, Maximilian Thiessen
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our main result is a complete characterization of the achievable learning rates in this model, revealing a trichotomy: exponential rates of the form e n arise precisely when the hypothesis class is finite; linear rates of the form d/n are achievable when a recently introduced combinatorial parameter, the VC-eluder dimension d, is finite; and arbitrarily slow rates may occur when d = . |
| Researcher Affiliation | Academia | Steve Hanneke Purdue University EMAIL Shay Moran Technion and Google Research EMAIL Maximilian Thiessen TU Wien EMAIL |
| Pseudocode | No | The paper contains no pseudocode or algorithm blocks. It focuses on theoretical proofs, definitions, and characterizations of learning rates. |
| Open Source Code | No | The Neur IPS Paper Checklist indicates 'NA' for 'Open access to data and code', and no explicit statement or link for code release is found within the paper. |
| Open Datasets | No | The paper is purely theoretical and does not conduct experiments on specific datasets. The Neur IPS Paper Checklist states 'NA' for questions related to experimental results and data. |
| Dataset Splits | No | The paper does not involve empirical experiments using datasets, therefore, there are no dataset splits described. |
| Hardware Specification | No | The paper is a theoretical work and does not describe any experiments that would require specific hardware. The Neur IPS Paper Checklist indicates 'NA' for questions related to experimental resources. |
| Software Dependencies | No | As this is a theoretical paper without experimental results, there are no software dependencies specified. |
| Experiment Setup | No | This theoretical paper does not include any experimental setup details such as hyperparameters or training configurations. |