Online Learning with Dependent Stochastic Feedback Graphs

Authors: Corinna Cortes, Giulia Desalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We present a detailed theoretical analysis of this algorithm, and also report the results of a series of experiments on real-world datasets, which show that our algorithm outperforms standard baselines for online learning with feedback graphs.
Researcher Affiliation Industry 1Google Research, New York, NY 2Hudson River Trading, New York, NY.
Pseudocode Yes The pseudocode of UCB-DSG is given in Algorithm 1.
Open Source Code No The information is insufficient because the paper does not contain an explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets Yes We present results for the CIFAR dataset, as well as ten datasets from the UCI repository: letter, pendigits, poker, satimage, shuttle, segment, covtype, acoustic, HIGGS and sensorless (see Appendix D for dataset statistics).
Dataset Splits No The information is insufficient because the paper mentions random shuffling and averaging over runs ('We randomly draw four times a set of hyperplanes...and for each set of hyperplanes, we randomly shuffle the data six times. Our results are averages over these 24 runs.'), but it does not specify explicit training, validation, and test dataset splits with percentages or sample counts, nor does it refer to predefined splits with citations for reproducibility.
Hardware Specification No The information is insufficient because the paper does not specify any particular hardware components such as GPU or CPU models, memory details, or specific cloud computing instances used for running the experiments.
Software Dependencies No The information is insufficient because the paper does not provide specific version numbers for any software dependencies, libraries, or programming languages used in the experiments.
Experiment Setup Yes The experiment was set up as follows. We randomly draw four times a set of hyperplanes... and for each set of hyperplanes, we randomly shuffle the data six times. Our results are averages over these 24 runs. For all algorithms...we introduced a parameter λ 2 [0.1, 0.5, 1, 10, 100], and tuned each algorithm over this parameter as is standard practice.