The Multi-fidelity Multi-armed Bandit

Authors: Kirthevasan Kandasamy, Gautam Dasarathy, Barnabas Poczos, Jeff Schneider

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we demonstrate that our algorithm outperforms naive UCB on simulations. 6 Some Simulations on Synthetic Problems
Researcher Affiliation Academia Carnegie Mellon University, Rice University {kandasamy, schneide, bapoczos}@cs.cmu.edu, gautamd@rice.edu
Pseudocode Yes Algorithm 1 MF-UCB
Open Source Code No The paper does not provide an explicit statement about open-source code availability, nor does it link to a code repository.
Open Datasets No The paper states using 'synthetic problems' with 'Gaussian rewards' and 'Bernoulli rewards' but does not provide access information (link, DOI, repository, or formal citation) for a publicly available or open dataset.
Dataset Splits No The paper uses 'synthetic problems' for its simulations but does not specify any dataset splits (e.g., percentages, sample counts, or predefined splits) for training, validation, or testing.
Hardware Specification No The paper describes 'simulations' but does not specify any hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not specify any software components or libraries with version numbers used in the experiments.
Experiment Setup No The paper mentions 'synthetic problems' and states that 'The details on these experiments are given in Appendix C', but the provided text does not contain specific experimental setup details such as hyperparameter values or training configurations.