Sparsity-Agnostic Lasso Bandit

Authors: Min-Hwan Oh, Garud Iyengar, Assaf Zeevi

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also comprehensively evaluate our proposed algorithm numerically and show that it consistently outperforms existing methods, even when the correct sparsity index is revealed to them but is kept hidden from our algorithm.
Researcher Affiliation Academia 1Seoul National University, Seoul, South Korea 2Columbia University, New York, NY, USA.
Pseudocode Yes Algorithm 1 SA LASSO BANDIT
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 describes generating features from distributions (multivariate Gaussian, uniform, elliptical) for its experiments but does not refer to or provide concrete access information for a specific, pre-existing publicly available dataset.
Dataset Splits No The paper is on contextual bandits, an online learning setting, and does not describe traditional train/validation/test dataset splits for reproducibility.
Hardware Specification No The paper does not provide any specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers used for its implementation or experiments.
Experiment Setup No The paper states that it conducts 20 independent runs for each experimental configuration and mentions the input parameter λ0 for SA LASSO BANDIT is derived as λ0 = 2σxmax, but it does not provide specific concrete numerical values for hyperparameters or other typical training configuration details like learning rates, batch sizes, or epochs.