Model Selection for Contextual Bandits

Authors: Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Additionally, Appendix A contains a validation experiment, where we demonstrate that Mod CB compares favorably to Lin UCB in simulations.
Researcher Affiliation Collaboration Dylan J. Foster Massachusetts Institute of Technology dylanf@mit.edu Akshay Krishnamurthy Microsoft Research NYC akshay@cs.umass.edu Haipeng Luo University of Southern California haipengl@usc.edu
Pseudocode Yes Algorithm 1 Mod CB (Model Selection for Contextual Bandits) ... Algorithm 2 Estimate Residual
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and refers to a 'validation experiment' in Appendix A but does not mention specific public datasets, nor does it provide any concrete access information (link, citation) for any dataset used.
Dataset Splits No The paper mentions a 'validation experiment' but does not provide specific details about training, validation, or test dataset splits.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., Python, PyTorch, specific solvers).
Experiment Setup No The paper is highly theoretical and describes algorithm parameters (e.g., C1, C2, µt, δ0) that are used in its theoretical guarantees, but it does not provide specific hyperparameter values or training configurations for a practical experiment setup in the main text.