Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization

Authors: Rad Niazadeh, Tim Roughgarden, Joshua Wang

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We further run experiments to verify the performance of our proposed algorithms in related machine learning applications.
Researcher Affiliation Collaboration Rad Niazadeh Department of Computer Science Stanford University, Stanford, CA 95130; Tim Roughgarden Department of Computer Science Stanford University, Stanford, CA 95130; Joshua R. Wang Google, Mountain View, CA 94043
Pseudocode Yes Algorithm 1: (Vanilla) Continuous Randomized Bi-Greedy; Algorithm 2: Binary-Search Continuous Bi-greedy
Open Source Code No The paper mentions Algorithms 3 and 4 are in the supplement and describes their implementation, but does not provide a direct link to open-source code for its methodology or explicitly state that the code is open-source.
Open Datasets No The paper discusses applications like Non-concave Quadratic Programming (NQP) and Softmax Extension for MAP inference of determinantal point processes, but does not name or provide access information for any specific public datasets used in the experiments.
Dataset Splits No The paper does not provide specific details on how the data was split into training, validation, or test sets, nor does it specify percentages or sample counts for these splits.
Hardware Specification No The paper states that experiments were implemented in Python but does not provide any specific details about the hardware (e.g., CPU, GPU models, memory, or cloud infrastructure) used to run these experiments.
Software Dependencies No The paper mentions that experiments were 'implemented in python' but does not specify the version of Python or any other software libraries or dependencies with their version numbers.
Experiment Setup No The paper states that 'Each experiment consists of twenty repeated trials' and 'n = 100 dimensional functions', but defers 'detailed specifics of each experiment' to the supplementary materials, thus not providing concrete hyperparameter values or comprehensive system-level training settings in the main text.