Almost Cost-Free Communication in Federated Best Arm Identification

Authors: Srinivas Reddy Kota, P. N. Karthik, Vincent Y. F. Tan

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

Reproducibility Variable Result LLM Response
Research Type Experimental We numerically validate the efficacy of FEDELIM on two synthetic datasets and the Movie Lens dataset.
Researcher Affiliation Academia Srinivas Reddy Kota, P. N. Karthik, and Vincent Y. F. Tan National University of Singapore Emails: ksvr1532@gmail.com, karthik@nus.edu.sg, vtan@nus.edu.sg
Pseudocode Yes Algorithm 1: Federated Learning Successive Elimination Algorithm (FEDELIM)
Open Source Code Yes The code used for obtaining the results may be accessed at https://github.com/ pnkarthik/AAAI-2023-Code.
Open Datasets Yes We numerically validate the efficacy of FEDELIM on two synthetic datasets and the Movie Lens dataset.
Dataset Splits No The paper mentions using 'synthetic datasets' and 'Movie Lens dataset' but does not specify any explicit training, validation, or test splits (e.g., percentages, sample counts, or predefined splits) for these datasets.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory, or cloud instances) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies (e.g., library names with version numbers like Python 3.8, PyTorch 1.9) required to replicate the experiments.
Experiment Setup No The paper describes the FEDELIM algorithm and its confidence parameters, but it does not specify concrete hyperparameters (e.g., learning rate, batch size, number of epochs) or system-level training settings that are typically provided in an experimental setup.