Rate-Optimal Subspace Estimation on Random Graphs

Authors: Zhixin Zhou, Fan Zhou, Ping Li, Cun-Hui Zhang

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments on the algorithms appear in Section 4. In this section, each experiment will repeat 100 times. In each iteration, the randomization procedure follows these steps:
Researcher Affiliation Collaboration 1Department of Management Sciences, City University of Hong Kong 2Cognitive Computing Lab, Baidu Research 3Department of Statistics, Rutgers University
Pseudocode Yes Algorithm 1 Hard Singular Value Thresholding Algorithm 2 Soft Singular Value Thresholding Algorithm 3 Singular space estimation
Open Source Code No The paper does not contain any explicit statements or links indicating that the source code for the described methodology is publicly available.
Open Datasets No The numerical experiments in Section 4 describe a procedure to 'Randomly generate matrices' and 'Generate the adjacency matrix of the random bipartite graph with connectivity matrix M', indicating the use of synthetically generated data rather than a publicly available dataset.
Dataset Splits No The paper describes a simulation setup where data is randomly generated for each experiment iteration (e.g., 'Randomly generate matrices M1...', 'Generate the adjacency matrix...'). It does not specify train, validation, or test splits of a fixed dataset.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory, or cloud instances) used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, or frameworks) used in the experiments.
Experiment Setup Yes We consider the following parameters in Θ1(n1, n2, r, p). n1 = n2 = 1000, r = 3, p = 0.01, 0.03, 0.05. In the following experiments, we vary the regularization constant c from 0.2 to 1, where the default constant equals to 2 in Algorithm 1.