Theoretical Analysis of Sparse Subspace Clustering with Missing Entries
Authors: Manolis Tsakiris, Rene Vidal
ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Figs. 1(a)-1(b) show the subspace preserving accuracy for both PZF-SSC and ZF-SSC, along with a fitted hyperbola (allowing for vertical and horizontal shift) for the phase transition region, the latter measured with a precision of 0.98. Figs. 1(c)-1(d) show the corresponding clustering accuracies produced by spectral clustering applied on the affinity graphs. Parameters are set as D = 100, ρ = 5, n = 3, λ = 10/ ζ. The complete data are unit norm, drawn uniformly at random from the subspaces, and each point is missing m = ωD entries also chosen uniformly at random. Results are averaged over 10 trials. |
| Researcher Affiliation | Academia | 1School of Information Science and Technology, Shanghai Tech University, Shanghai, China. 2Mathematical Institute for Data Science and Department of Biomedical Engineering, Johns Hopkins University, Baltimore, USA. |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to its own source code for the methodology described. |
| Open Datasets | No | The complete data are unit norm, drawn uniformly at random from the subspaces, and each point is missing m = ωD entries also chosen uniformly at random. |
| Dataset Splits | No | The paper does not specify train/validation/test dataset splits. Data is generated synthetically for experiments, not from a pre-existing dataset with standard splits. |
| Hardware Specification | No | The paper does not provide specific hardware details used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | Yes | Parameters are set as D = 100, ρ = 5, n = 3, λ = 10/ ζ. The complete data are unit norm, drawn uniformly at random from the subspaces, and each point is missing m = ωD entries also chosen uniformly at random. Results are averaged over 10 trials. |