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..
Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
Authors: Jongyeong Lee, Junya Honda, Shinji Ito, Min-hwan Oh
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | 3. Theory assumptions and proofs: For most of our theoretical results, we explicitly state the required assumptions. However, some technical conditions specific to Fréchet-type distributions are deferred to Appendix A.1 to avoid unnecessary distractions in the main text. For completeness, all detailed proofs are provided in the appendix. [...] 7. Experiment statistical significance: NA (We do not include experimental results that needs any kind of statistical significance testing.) [...] 9. Code of ethics: This is a theoretical work. |
| Researcher Affiliation | Academia | Jongyeong Lee Korea Institute of Science and Technology EMAIL Junya Honda Kyoto University, RIKEN AIP EMAIL Shinji Ito The University of Tokyo, RIKEN AIP EMAIL Min-hwan Oh Seoul National University EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. It primarily presents mathematical derivations, theorems, and proofs. |
| Open Source Code | Yes | 5. Open access to data and code: Answer: [No] Justification: We provide the full codes in Appendix F. [...] In this section, we provide the Matlab code for the inverse Fourier transform (IFT) and additional plots to confirm whether the obtained IFT is real-valued. |
| Open Datasets | No | 7. Experiment statistical significance: NA (We do not include experimental results that needs any kind of statistical significance testing.) The paper does not mention any specific open datasets used for empirical evaluation. It focuses on theoretical analysis of multi-armed bandit problems. |
| Dataset Splits | No | The paper does not describe any dataset splits, as it does not report on empirical experiments using specific datasets. |
| Hardware Specification | No | 8. Experiments compute resources: Answer: [No] Justification: Our code is very light and can be run on any recent computer or laptop without special hardware requirements. |
| Software Dependencies | No | The paper mentions the use of 'Matlab code' and 'Char Fun Tool [53, 54]' in Appendix F for numerical validation but does not provide specific version numbers for these software dependencies. |
| Experiment Setup | No | The paper does not provide details on specific experimental setup, hyperparameters, or training configurations, as its focus is on theoretical contributions rather than empirical experiments. |