Decomposable Submodular Function Minimization: Discrete and Continuous

Authors: Alina Ene, Huy Nguyen, László A. Végh

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our paper establishes connections between discrete and continuous methods for DSFM, as well as provides a systematic experimental comparison of these approaches.
Researcher Affiliation Academia Department of Computer Science, Boston University, aene@bu.edu College of Computer and Information Science, Northeastern University, hu.nguyen@northeastern.edu Department of Mathematics, London School of Economics, L.Vegh@lse.ac.uk
Pseudocode No The paper describes algorithms (e.g., alternating projections, random coordinate descent) but does not provide pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit links to source code for the methodology described, nor does it state that the code is publicly available.
Open Datasets Yes The data is available at http://melodi.ee.washington.edu/~jegelka/cc/index.html and http://research.microsoft.com/en-us/um/cambridge/projects/visionimagevideoediting/ segmentation/grabcut.htm
Dataset Splits No The paper does not provide specific details on training, validation, or test dataset splits (e.g., percentages or sample counts). It mentions using "five image segmentation instances" for evaluation.
Hardware Specification Yes The experiments were carried out on a single computer with a 3.3 GHz Intel Core i5 processor and 8 GB of memory
Software Dependencies No The paper mentions several algorithms and tools (RCDM, ACDM, Submodular IBFS, Fujishige-Wolfe, general QP solver), but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes At every iteration, we ran Fujishige-Wolfe for 10 iterations only, but we warm-started with the current solution xi B(fi) for each i [r].