Indexed Minimum Empirical Divergence for Unimodal Bandits
Authors: Hassan SABER, Pierre Ménard, Odalric-Ambrym Maillard
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Numerical experiments show that IMED-UB competes with the state-of-the-art algorithms. |
| Researcher Affiliation | Academia | Hassan Saber Université de Lille, Inria, CNRS, Centrale Lille UMR 9189 CRISt AL, F-59000 Lille, France hassan.saber@inria.fr Pierre Ménard Otto von Guericke Universität Magdeburg pierre.menard@ovgu.de Odalric-Ambrym Maillard Université de Lille, Inria, CNRS, Centrale Lille UMR 9189 CRISt AL, F-59000 Lille, France odalric.maillard@inria.fr |
| Pseudocode | Yes | Algorithm 1 IMED-UB Pull each arm once for t = |A| . . . T 1 do Choose ba t argmin ba b A (t) Nba (t) (chosen arbitrarily) Pull at+1 argmin a {ba t } Vba t Ia(t) (chosen arbitrarily) |
| Open Source Code | No | The paper does not provide any specific links or statements about the availability of open-source code for the methodology described. |
| Open Datasets | No | The paper uses synthetic data generated under Bernoulli, Gaussian, or Exponential distribution assumptions, defined by a vector of means. It does not provide access information for a fixed, publicly available dataset. |
| Dataset Splits | No | The paper describes experiments based on simulated data generated from specified distributions, but it does not provide specific dataset split information (e.g., percentages, sample counts, or predefined splits) for training, validation, or testing. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | For the experiments we consider a graph G with maximal degree d = 2 and the unimodal unimodal vectors of means µ = (0.05, 0.10, 0.15, 0.20, 0.25, 0.20, 0.15, 0.10, 0.05), and average regrets over 500 runs for each distribution family. |