Cascading Non-Stationary Bandits: Online Learning to Rank in the Non-Stationary Cascade Model

Authors: Chang Li, Maarten de Rijke

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

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we evaluate their performance on a realworld web search click dataset.
Researcher Affiliation Academia Chang Li and Maarten de Rijke University of Amsterdam {c.li, derijke}@uva.nl
Pseudocode Yes Algorithm 1: UCB-type algorithm for Cascading nonstationary bandits.
Open Source Code No The paper mentions using a tool named Py Click and provides a link to its GitHub repository (https://github.com/markovi/Py Click), but it does not state that the authors' own code for the described methodology or experiments is open-sourced or provided.
Open Datasets Yes We evaluate Cascade DUCB and Cascade SWUCB on the Yandex click dataset,2 which is the largest public click collection. 2https://academy.yandex.ru/events/data analysis/relpred2011
Dataset Splits No The paper discusses simulation setup and online learning steps but does not explicitly describe train/validation/test dataset splits with percentages or sample counts for reproducing the experiments.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as GPU or CPU models.
Software Dependencies No The paper mentions using "Py Click" (Py Click.3) but does not provide a specific version number for it or any other software dependencies crucial for reproduction.
Experiment Setup Yes In experiments, we set = 0.5, γ = 1 1/(4pn) and = 2 p n ln(n), the values that roughly minimize the upper bounds. In our experiment, we set m1 = m2 = 10k and choose 10 breakpoints. In total, we run experiments for 100k steps.