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..
Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
Authors: Ofir Schlisselberg, Tal Lancewicki, Peter Auer, Yishay Mansour
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The paper presents theoretical results, algorithms, proofs, and analyses of regret bounds in multi-armed bandit problems. The 'NeurIPS Paper Checklist' section explicitly states 'The paper does not include experiments.' for questions related to reproducibility, open access to data and code, experimental settings, statistical significance, and compute resources. |
| Researcher Affiliation | Collaboration | Ofir Schlisselberg, Tal Lancewicki, and Yishay Mansour are affiliated with Tel Aviv University (academic). Peter Auer is affiliated with Technical University of Leoben (academic). Yishay Mansour is also affiliated with Google Research (industry). The presence of both academic (Tel Aviv University, Technical University of Leoben) and industry (Google Research) affiliations indicates a collaborative effort. |
| Pseudocode | Yes | The paper includes 'Algorithm 2 Sketch of Delayed SAPO Algorithm', 'Algorithm 5 Delayed SAPO Algorithm', 'Procedure 3 Basic Stochastic Checks (BSC) Subroutine', 'Procedure 4 Sketch of Eliminated Arms Processing (EAP) Subroutine', 'Procedure 6 Eliminated Arms Processing (EAP) Subroutine', 'Procedure 7 Basic Stochastic Checks (BSC) Subroutine', 'Algorithm 8 Delayed SAPO Algorithm with reduced log (K)', and 'Procedure 9 Basic Stochastic Checks (BSC) Subroutine with reduced log (K)'. |
| Open Source Code | No | The paper does not contain any statement about releasing source code or provide a link to a code repository. The NeurIPS Paper Checklist also explicitly states, 'The paper does not include experiments requiring code.' |
| Open Datasets | No | The paper is theoretical and does not conduct experiments using datasets. The NeurIPS Paper Checklist states, 'The paper does not include experiments.' |
| Dataset Splits | No | The paper is theoretical and does not conduct experiments using datasets, thus no dataset splits are discussed. The NeurIPS Paper Checklist states, 'The paper does not include experiments.' |
| Hardware Specification | No | The paper is theoretical and does not describe any experiments that would require hardware. The NeurIPS Paper Checklist states, 'The paper does not include experiments.' |
| Software Dependencies | No | The paper is theoretical and does not describe any experimental setup that would involve specific software dependencies with version numbers. The NeurIPS Paper Checklist states, 'The paper does not include experiments.' |
| Experiment Setup | No | The paper is theoretical and focuses on algorithm design and mathematical proofs, not on experimental results or their setup. The NeurIPS Paper Checklist states, 'The paper does not include experiments.' |