Nearest Neighbour with Bandit Feedback

Authors: Stephen Pasteris, Chris Hicks, Vasilios Mavroudis

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We give generic regret bounds for our algorithm and further analyse them when applied to the stochastic bandit problem in euclidean space. In Appendix E we prove, in order, all of the theorems stated in this paper.
Researcher Affiliation Academia Stephen Pasteris The Alan Turing Institute London UK spasteris@turing.ac.uk Chris Hicks The Alan Turing Institute London UK c.hicks@turing.ac.uk Vasilios Mavroudis The Alan Turing Institute London UK vmavroudis@turing.ac.uk
Pseudocode Yes Algorithm 1 CANPROP at trial t
Open Source Code No The paper does not provide any statement or link indicating the release of open-source code for the described methodology.
Open Datasets No The paper describes a theoretical problem setting involving data, but does not mention the use or availability of a specific publicly accessible dataset for experimental purposes.
Dataset Splits No The paper is theoretical and does not describe empirical experiments, thus no dataset split information (training, validation, test) is provided.
Hardware Specification No The paper is theoretical and does not report on experiments requiring specific hardware; therefore, no hardware specifications are mentioned.
Software Dependencies No The paper provides pseudocode for algorithms but does not specify any software dependencies with version numbers required for implementation.
Experiment Setup No The paper is theoretical and does not describe empirical experiments; therefore, no experimental setup details such as hyperparameters or training settings are provided.