Replication-proof Bandit Mechanism Design with Bayesian Agents

Authors: Suho Shin, Seyed A. Esmaeili, MohammadTaghi Hajiaghayi

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide sufficient and necessary conditions for an algorithm to be replication-proof in the single-agent setting, and present an algorithm that satisfies these properties. These results center around several analytical theorems that focus on comparing the expected regret of multiple bandit instances, and therefore might be of independent interest since they have not been studied before to the best of our knowledge. We expand this result to the multi-agent setting, and provide a replication-proof algorithm for any problem instance. We finalize our result by proving its sublinear regret upper bound which matches that of Shin, Lee and Ok AISTATS 22.
Researcher Affiliation Academia Suho Shin1, Seyed A. Esmaeili2, Mohammad Taghi Hajiaghayi1 1 University of Maryland 2 University of Chicago (suhoshin,hajiagha)@umd.edu,EMAIL
Pseudocode Yes Its pseudocode is presented in Algorithm 3 in the appendix. [...] We present H-ETC-R presented in Algorithm 5 in the appendix
Open Source Code No The paper does not contain any explicit statements or links indicating the release of source code for the described methodology.
Open Datasets No The paper discusses theoretical problem instances related to multi-armed bandit algorithms and does not mention or provide access information for any specific publicly available datasets used for empirical evaluation.
Dataset Splits No The paper does not describe any empirical experiments using datasets, therefore, no dataset split information is provided.
Hardware Specification No The paper focuses on theoretical contributions and algorithm design. It does not describe any empirical experiments or provide details on hardware specifications used for running experiments.
Software Dependencies No The paper primarily presents theoretical results and algorithms. It does not describe any empirical experiments or list specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical in nature, focusing on algorithm design and proofs. It does not describe any specific experimental setup details, hyperparameters, or training configurations.