Non-monotone DR-submodular Maximization over General Convex Sets

Authors: Christoph Dürr, Nguyen Kim Thang, Abhinav Srivastav, Léo Tible

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

Reproducibility Variable Result LLM Response
Research Type Experimental Finally we benchmark our algorithm on problems arising in machine learning domain with the real-world datasets.
Researcher Affiliation Academia 1LIP6, Sorbonne University, France 2IBISC, Univ Évry, University Paris-Saclay, France
Pseudocode Yes Algorithm 1 Frank-Wolfe Algorithm
Open Source Code Yes The source code is available at https://sites.google.com/ site/abhinavsriva/ijcai-20-code and https://www.ibisc.univ-evry.fr/~thang
Open Datasets No The paper mentions using 'Advogato network with 6.5K users (vertices) and 61K connections (edges)' and 'synthetic quadratic objectives', but does not provide concrete access information (link, DOI, or specific citation for public access) for either. For synthetic data, it describes generation, but this isn't a public dataset in the sense of being provided externally with access info.
Dataset Splits No The paper does not provide specific dataset split information for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory) used for running its experiments.
Software Dependencies No The paper mentions 'MATLAB using CPLEX optimization tool', but does not provide a specific version number for CPLEX or MATLAB.
Experiment Setup Yes All experiments are performed in MATLAB using CPLEX optimization tool on MAC OS version 10.142. ... We run all the algorithms for 100 iterations. All the results are the average of 20 repeated experiments. ... we set p = 0.0001.