Combinatorial semi-bandit with known covariance

Authors: Rémy Degenne, Vianney Perchet

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

Reproducibility Variable Result LLM Response
Research Type Experimental Figure 1: Left: parallel paths problem. Right: regret of OLS-UCB as a function of m and γ in the parallel paths problem with 5 paths (average over 1000 runs).
Researcher Affiliation Collaboration Rémy Degenne LMPA, Université Paris Diderot CMLA, ENS Paris-Saclay degenne@cmla.ens-cachan.fr Vianney Perchet CMLA, ENS Paris-Saclay CRITEO Research, Paris perchet@normalesup.org
Pseudocode Yes Algorithm 1 OLS-UCB. Require: Positive semi-definite matrix Γ, real parameter λ > 0.
Open Source Code No The paper does not contain any statement or link indicating that the source code for the methodology is openly available.
Open Datasets No The paper discusses theoretical bandit problems and simulations (e.g., 'parallel paths problem') but does not use a publicly available or open dataset with access information.
Dataset Splits No The paper does not specify training, validation, or test dataset splits. Its evaluation is based on theoretical analysis and simulations, not traditional dataset splits.
Hardware Specification No The paper does not provide any specific details about the hardware used for running experiments, such as CPU or GPU models.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, or other libraries).
Experiment Setup No The paper mentions algorithm parameters like 'λ > 0' but does not provide specific hyperparameter values, training configurations, or system-level settings typically found in empirical experimental setups.