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..
Protocols for Verifying Smooth Strategies in Bandits and Games
Authors: Miranda Christ, Daniel Reichman, Jonathan Shafer
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We prove that such verification is possible for sufficiently smooth strategies that do not put too much probability mass on any specific action and provide protocols for verifying that a smooth policy for a multi-armed bandit is close to optimal. Our verification protocols require provably fewer arm queries than learning. Furthermore, we show how to use cryptographic tools to reduce the communication cost of our protocols. We complement our protocol by proving a nearly tight lower bound on the query complexity of verification in our settings. As an application, we use our bandit verification protocol to build a protocol for verifying approximate optimality of a strong smooth Nash equilibrium, with sublinear query complexity. |
| Researcher Affiliation | Academia | Miranda Christ Columbia University EMAIL Daniel Reichman Worcester Polytechnic Institute EMAIL Jonathan Shafer MIT EMAIL |
| Pseudocode | Yes | The pseudocode of the verification protocol and the proof of Theorem 5.5 appear in the Multi-armed bandits Section in the Supplementary Material. |
| Open Source Code | No | Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [NA] Justification: No code or data in the paper (other than pseudocode visible to everyone reading the paper) |
| Open Datasets | No | Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [NA] Justification: No code or data in the paper (other than pseudocode visible to everyone reading the paper) |
| Dataset Splits | No | This paper does not include experiments or datasets, therefore, there is no information regarding dataset splits. |
| Hardware Specification | No | Question: For each experiment, does the paper provide sufficient information on the computer resources (type of compute workers, memory, time of execution) needed to reproduce the experiments? Answer: [NA] Justification: No experiments in the paper |
| Software Dependencies | No | This paper is purely theoretical and describes algorithms and protocols without discussing specific software implementations or dependencies with version numbers. |
| Experiment Setup | No | Question: Does the paper specify all the training and test details (e.g., data splits, hyperparameters, how they were chosen, type of optimizer, etc.) necessary to understand the results? Answer: [NA] Justification: No experiments in the paper |