Reduction Techniques for Graph-Based Convex Clustering

Authors: Lei Han, Yu Zhang

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on both synthetic and real-world datasets show that our methods can largely improve the efficiency of the GCC model.
Researcher Affiliation Academia 1Department of Statistics, Rutgers University 2Department of Computer Science and Engineering, Hong Kong University of Science and Technology
Pseudocode No The paper presents mathematical formulations and theorems, but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not explicitly state that source code for their methodology is provided, nor does it include a link to a code repository. It only references supplementary material for 'details'.
Open Datasets Yes We test the Eater and Cigar rules on two UCI datasets, i.e., the iris and vehicle datasets. https://archive.ics.uci.edu/ml/datasets.html
Dataset Splits No The paper does not explicitly provide details about training, validation, or test dataset splits (e.g., percentages, counts, or cross-validation setup). It only specifies the number of data points generated and the sequence of regularization parameters.
Hardware Specification Yes All the experiments are conducted on a machine with Intel i7 CPU and 8GB RAM under the Matlab 2013b environment.
Software Dependencies Yes All the experiments are conducted on a machine with Intel i7 CPU and 8GB RAM under the Matlab 2013b environment.
Experiment Setup Yes the weight before any data pair (i, j) is defined as wij = exp γ xi xj 2 2 , and we use γ = 10/ d2, where d is the average ℓ2 distance for all possible pairs of data points. In the experiments, q is set to be 2. We use the FISTA (Beck and Teboulle 2009) algorithm to solve problem (5) for the TCC model. For the CGCC model, we use the ADMM method to solve it.