Online Second Price Auction with Semi-Bandit Feedback under the Non-Stationary Setting

Authors: Zhao Haoyu, Chen Wei6893-6900

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical To our knowledge, this paper is the first to study the repeated auction in the non-stationary setting theoretically. Our algorithm achieves the non-stationary regret upper bound O(min{ ST, V 1 3 T 2 3 }), where S is the number of switches in the distribution, and V is the sum of total variation, and S and V are not needed to be known by the algorithm. We also prove regret lower bounds Ω( ST) in the switching case and Ω( V 1 3 T 2 3 ) in the dynamic case, showing that our algorithm has nearly optimal non-stationary regret.
Researcher Affiliation Collaboration Haoyu Zhao,1 Wei Chen2 1IIIS, Tsinghua University, Beijing, China 2Microsoft Research, Beijing, China zhaohy16@mails.tsinghua.edu.cn, weic@microsoft.com
Pseudocode Yes Algorithm 1: Elim-NS
Open Source Code No The paper mentions a technical report on arXiv (Zhao and Chen 2019a) but does not provide any links to open-source code for the described methodology.
Open Datasets No The paper is theoretical and focuses on algorithm design and regret analysis; it does not perform empirical experiments with datasets, thus no training dataset information is provided.
Dataset Splits No The paper is theoretical and focuses on algorithm design and regret analysis; it does not perform empirical experiments with datasets, thus no validation dataset split information is provided.
Hardware Specification No The paper is theoretical and does not describe any empirical experiments, therefore no specific hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe any empirical experiments or their implementation, therefore no specific software dependencies with version numbers are provided.
Experiment Setup No The paper is theoretical and does not describe empirical experiments, so it does not provide details on experimental setup such as hyperparameters or training settings.