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..

Data-Dependent Regret Bounds for Constrained MABs

Authors: Gianmarco Genalti, Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper initiates the study of data-dependent regret bounds in constrained MAB settings... We design an algorithm with a regret bound consisting of two data-dependent terms. The first one captures the difficulty of satisfying the constraints, while the second one encodes the complexity of learning independently of their presence. We also prove a lower bound showing that these two terms are not artifacts of our specific approach and analysis, but rather the fundamental components that inherently characterize the problem complexity. Finally, in designing our algorithm, we also derive some novel results in the related (and easier) soft constraints settings, which may be of independent interest. (From abstract) -- Question: Does the paper fully disclose all the information needed to reproduce the main experimental results of the paper... Answer: [NA] Justification: The paper does not include experiments.
Researcher Affiliation Academia Gianmarco Genalti Politecnico di Milano EMAIL Francesco Emanuele Stradi Politecnico di Milano EMAIL Matteo Castiglioni Politecnico di Milano EMAIL Alberto Marchesi Politecnico di Milano EMAIL Nicola Gatti Politecnico di Milano EMAIL
Pseudocode Yes Algorithm 1 COLB; Algorithm 2 SOLB
Open Source Code No The paper does not include any explicit statement about releasing code or a link to a code repository. The NeurIPS Paper Checklist for 'Open access to data and code' states: 'Answer: [NA] Justification: The paper does not include experiments.'
Open Datasets No The paper does not describe or use any specific dataset for experiments. The NeurIPS Paper Checklist for 'Open access to data and code' states: 'Answer: [NA] Justification: The paper does not include experiments.'
Dataset Splits No The paper does not perform experiments or use datasets that would require splits. The NeurIPS Paper Checklist for 'Experimental result reproducibility' states: 'Answer: [NA] Justification: The paper does not include experiments.'
Hardware Specification No The paper is theoretical and does not describe any experimental hardware setup. The NeurIPS Paper Checklist for 'Experiments compute resources' states: 'Answer: [NA] Justification: The paper does not include experiments.'
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers for experimental reproducibility. The NeurIPS Paper Checklist for 'Experimental result reproducibility' states: 'Answer: [NA] Justification: The paper does not include experiments.'
Experiment Setup No The paper does not include experiments and thus does not describe any experimental setup or hyperparameters. The NeurIPS Paper Checklist for 'Experimental setting/details' states: 'Answer: [NA] Justification: The paper does not include experiments.'