The Information-Theoretic Requirements of Subspace Clustering with Missing Data

Authors: Daniel Pimentel-Alarcon, Robert Nowak

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

Reproducibility Variable Result LLM Response
Research Type Experimental In Section 3 we also present experiments showing that our theory accurately predicts the performance of SCMD algorithms from the literature.
Researcher Affiliation Academia Daniel L. Pimentel-Alarc on PIMENTELALAR@WISC.EDU Robert D. Nowak NOWAK@ECE.WISC.EDU University of Wisconsin Madison, 53706 USA
Pseudocode Yes Algorithm 1 Subspace Clustering Certification. Algorithm 2 Determine whether Ωτ satisfies (i).
Open Source Code No The paper does not provide any explicit statement or link for open-source code availability.
Open Datasets No The paper mentions 'using EM (Pimentel-Alarc on et al., 2014) and SSC-EWZF (Yang et al., 2015)' for experiments but does not name a specific public dataset or provide access information for any dataset used for training or evaluation.
Dataset Splits No The paper mentions a 'training set' and 'hold-out set' in the context of the proposed certification algorithm (Algorithm 1) but does not provide specific details (percentages, counts, or methodology) for data splitting in the experimental evaluation presented in Figure 3.
Hardware Specification No The paper does not provide any specific hardware details used for running the experiments.
Software Dependencies No The paper mentions algorithms like 'EM (Pimentel-Alarc on et al., 2014) and SSC-EWZF (Yang et al., 2015)' but does not specify version numbers for any software dependencies.
Experiment Setup No Figure 3 mentions experimental parameters 'K = 5 subspaces of dimension r = 25, in ambient dimension d = 100'. However, it does not provide specific hyperparameter values or detailed training configurations for the SCMD algorithms (EM, SSC-EWZF) used in the experiments.