Combinatorial Bandits Revisited

Authors: Richard Combes, Mohammad Sadegh Talebi Mazraeh Shahi, Alexandre Proutiere, marc lelarge

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments for some specific combinatorial problems are presented in the supplementary material, and show that ESCB significantly outperforms existing algorithms.
Researcher Affiliation Academia Centrale-Supelec, L2S, Gif-sur-Yvette, FRANCE Department of Automatic Control, KTH, Stockholm, SWEDEN INRIA & ENS, Paris, FRANCE
Pseudocode Yes Algorithm 1 ESCB; Algorithm 2 COMBEXP
Open Source Code No The paper mentions numerical experiments are in supplementary material but does not explicitly state that source code is provided or offer a link to a repository.
Open Datasets No The paper describes the problem and algorithms but does not mention specific public datasets by name or provide access information for any datasets used in experiments.
Dataset Splits No The paper discusses regret bounds and algorithm complexity but does not provide specific details on training, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper mentions numerical experiments but does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings in the main text.