Communication-Efficient Collaborative Best Arm Identification

Authors: Nikolai Karpov, Qin Zhang

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

Reproducibility Variable Result LLM Response
Research Type Experimental We give both algorithmic and impossibility results, and conduct a set of experiments to demonstrate the effectiveness of our algorithms.
Researcher Affiliation Academia Indiana University Bloomington nkarpov@iu.edu, qzhangcs@indiana.edu
Pseudocode Yes The algorithm for top-m arm identification in the IID data setting is described in Algorithm 1. [...] Algorithm 2: LOCALELIM(r) [...] Algorithm 3: GLOBALELIM(r)
Open Source Code No The paper does not contain any explicit statement about releasing the source code for the methodology, nor does it provide a link to a code repository.
Open Datasets Yes We use a real-world dataset Movie Lens (Harper and Konstan 2016).
Dataset Splits No The paper mentions using the Movie Lens dataset but does not provide specific details on training, validation, or test splits (e.g., percentages, sample counts, or citations to predefined splits).
Hardware Specification Yes All experiments were conducted in Power Edge R740 server equipped 2 Intel Xeon Gold 6248R 3.0 GHz (24-core/48-thread per CPU) and 256GB RAM.
Software Dependencies No The paper states 'All algorithms are implemented using programming language Kotlin.' However, it does not provide specific version numbers for Kotlin or any other libraries/frameworks used.
Experiment Setup No The paper describes the algorithms and their performance, but it does not specify concrete hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations for the experiments.