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..

An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction

Authors: Tim van Erven, Jack Mayo, Julia Olkhovskaya, Chen-Yu Wei

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This is a theory paper without experiments. This is theoretical work, which did not require human subjects or participants, and involved no data. It contributes to the fundamental understanding of contextual bandits, without any direct foreseeable negative societal impact. Mitigation measures were therefore not applicable. This is theoretical work, which contributes to the fundamental understanding of contextual bandits.
Researcher Affiliation Academia University of Amsterdam. Email: EMAIL University of Amsterdam; Kurtos.ai. Email: EMAIL Delft University of Technology. Email: EMAIL University of Virginia. Email: EMAIL
Pseudocode Yes Algorithm 1: Adversarial Linear Contextual Bandits Algorithm 2: Misspecification-Robust Continuous Exponential Weights
Open Source Code No The paper does not include experiments requiring data or code.
Open Datasets No This is a theory paper without experiments.
Dataset Splits No The paper does not include experiments.
Hardware Specification No The paper does not include experiments.
Software Dependencies No The paper does not include experiments.
Experiment Setup No The paper does not include experiments.