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..

Agnostic Active Learning Is Always Better Than Passive Learning

Authors: Steve Hanneke

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This work resolves a long-standing open question of central importance to the theory of active learning, closing a qualitative and quantitative gap in our understanding of active learning in the non-realizable case. We provide the first sharp characterization of the optimal first-order query complexity of agnostic active learning, and propose a new general active learning algorithm which achieves it.
Researcher Affiliation Academia Steve Hanneke Department of Computer Science Purdue University EMAIL
Pseudocode Yes Figure 1: The AVID Agnostic algorithm.
Open Source Code No The paper does not contain any explicit statements about releasing source code, nor does it provide any links to code repositories. The NeurIPS checklist states that it is a purely theoretical work and does not include an experimental component relying on data or code.
Open Datasets No The paper does not use or provide any specific datasets for experimental evaluation. The NeurIPS checklist states that it is a purely theoretical work and does not include an experimental component relying on data or code.
Dataset Splits No This is a purely theoretical work and does not involve experimental evaluation on datasets, thus dataset splits are not applicable.
Hardware Specification No This is a purely theoretical work and does not involve experimental evaluation, thus hardware specifications are not applicable.
Software Dependencies No This is a purely theoretical work and does not involve experimental evaluation, thus software dependencies are not applicable.
Experiment Setup No This is a purely theoretical work and does not involve experimental evaluation, thus experimental setup details are not applicable.