Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret

Authors: Alina Beygelzimer, Francesco Orabona, Chicheng Zhang

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We test our algorithm experimentally, showing that it also performs favorably against earlier algorithms.
Researcher Affiliation Collaboration 1Yahoo Research, New York, NY 2Stony Brook University, Stony Brook, NY 3University of California, San Diego, La Jolla, CA.
Pseudocode Yes Algorithm 1 Second Order Banditron Algorithm (SOBA)
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the described methodology.
Open Datasets Yes We used three different datasets from Kakade et al. (2008): Syn Sep, Syn Non Sep, Reuters4. The first two are synthetic, with 10^6 samples in R^400 and 9 classes. [...] We also report the performance on Covtype from Lib SVM repository.
Dataset Splits No The paper mentions datasets used but does not provide specific training/validation/test split percentages, sample counts, or references to predefined splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions algorithms implemented but does not list specific software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes In the experiments, we only changed the exploration rate γ, leaving fixed all the other parameters the algorithms might have. In particular, for the PNewtron we set α = 10, β = 0.01, and D = 1, as in Hazan & Kale (2011). In SOBA, a is fixed to 1 in all the experiments.