Cone-Constrained Principal Component Analysis

Authors: Yash Deshpande, Andrea Montanari, Emile Richard

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We performed numerical experiments on synthetic data generated according to the model (1) and with signal v0 = u(n, nε) as defined in the previous section. We provide in the Appendix formulas for the value of limn v0, bv ML , which correspond to continuous black lines in the Figure 1. We compare these predictions with empirical values obtained by running AMP.
Researcher Affiliation Academia Yash Deshpande Electrical Engineering Stanford University Andrea Montanari Electrical Engineering and Statistics Stanford University Emile Richard Electrical Engineering Stanford University
Pseudocode No The algorithms are described using mathematical equations (6), (7), and AMP, but are not presented in formal pseudocode or algorithm blocks.
Open Source Code No No statement or link providing concrete access to source code for the methodology was found.
Open Datasets No The paper uses 'synthetic data generated according to the model (1)' but provides no access information (link, citation, or repository) for this data.
Dataset Splits No No specific dataset split information (e.g., percentages, sample counts, or predefined splits with citations) for training, validation, or test sets was found.
Hardware Specification No No specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running the experiments were provided.
Software Dependencies No No specific software dependencies with version numbers (e.g., libraries, frameworks, or operating systems) were provided.
Experiment Setup Yes We generated samples of size n = 104, sparsity level ε {0.001, 0.1, 0.8}, and signal-to-noise ratios β {0.05, 0.10, . . . , 1.5}. In each case we run AMP for t = 50 iterations and plot the empirical average of bvt, v0 over 32 instances.