Federated Linear Bandits with Finite Adversarial Actions

Authors: Li Fan, Ruida Zhou, Chao Tian, Cong Shen

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiment results corroborate the theoretical analysis and demonstrate the effectiveness of Fed Sup Lin UCB on both synthetic and realworld datasets.
Researcher Affiliation Academia Li Fan University of Virginia lf2by@virginia.edu Ruida Zhou Texas A&M University ruida@tamu.edu Chao Tian Texas A&M University chao.tian@tamu.edu Cong Shen University of Virginia cong@virginia.edu
Pseudocode Yes Algorithm 1 Sync(s, server, client 1, . . . client n); Algorithm 2 S-LUCB; Algorithm 3 Async-Fed Sup Lin UCB; Algorithm 4 Sync-Fed Sup Lin UCB
Open Source Code No The paper does not include any explicit statement or link indicating the release of open-source code for the described methodology.
Open Datasets Yes We have carried out experiments utilizing the real-world recommendation dataset Movie Lens 20M (Harper and Konstan, 2015).
Dataset Splits No The paper mentions using datasets but does not provide specific training/validation/test split percentages, sample counts, or explicit instructions for dataset partitioning.
Hardware Specification No The paper describes experiment results using synthetic and real-world datasets but does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running these experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper mentions parameters like T, M, d, A for synthetic data and TF-IDF feature d=25, K=20 for real-world data, but does not provide specific hyperparameters (e.g., learning rate, batch size, optimizer settings) or detailed system-level training configurations.