Decentralized Learning in Online Queuing Systems

Authors: Flore Sentenac, Etienne Boursier, Vianney Perchet

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Section 5 finally compares the behavior of ADEQUA with no-regret strategies on toy examples and empirically confirms the different known theoretical results. and Figures 2 and 3 compare on toy examples the stability of queues, when either each of them follows the no-regret strategy EXP3.P.1, or each queue follows ADEQUA.
Researcher Affiliation Collaboration Flore Sentenac CREST, ENSAE Paris, Palaiseau, France flore.sentenac@gmail.com, Etienne Boursier Centre Borelli, ENS Paris-Saclay, France etienne.boursier1@gmail.com, Vianney Perchet CREST, ENSAE Paris, Palaiseau, France CRITEO AI Lab, Paris, France vianney.perchet@normalesup.org
Pseudocode Yes Algorithm 1: ADEQUA and Algorithm 2: EXPLORE
Open Source Code Yes The code for the experiments is available at gitlab.com/f_sen/queuing_systems.
Open Datasets No The paper uses toy examples with specified parameters (e.g., λi = (N + 1)/N 2. Moreover µ1 = 1 and for all i 2, µi = (N 1)/N 2) rather than providing access information for a publicly available dataset.
Dataset Splits No The paper describes using toy examples for simulations but does not provide specific train/validation/test dataset split information.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers required to replicate the experiment.
Experiment Setup Yes For practical considerations, we choose the exploration probability εt = (N + K)t 1/4 for ADEQUA, as the exploration is too slow with εt of order t 1/5. and The code for the experiments is available at gitlab.com/f_sen/queuing_systems.