Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds

Authors: Yuchen Zhang, Martin Wainwright, Michael Jordan

ICML 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the practical effectiveness of the proposed algorithm with some numerical experiments.
Researcher Affiliation Academia Yuchen Zhang YUCZHANG@EECS.BERKELEY.EDU University of California, Berkeley, CA 94720, USA
Pseudocode Yes Algorithm 1 Evaluation of Chebyshev Polynomial Algorithm 2 Randomized Algorithm for Rank 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 paper describes generating its own synthetic data for experiments (
Dataset Splits No The paper describes generating synthetic data and evaluating the mean squared error over 100 independent runs of the algorithm. It does not mention or specify any train/validation/test dataset splits.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as GPU or CPU models.
Software Dependencies No The paper does not specify any software dependencies with version numbers used for the experiments.
Experiment Setup Yes In order to generate the data, we choose the parameters r = 100, λ = 0.4 and σ2 = 0.1. These choices motivate the thresholds c1 = λ + σ2 = 0.5 and c2 = σ2 = 0.1 in Algorithm 2. We illustrate the behavior of the algorithm for three different choices of the degree parameter p — specifically, p ∈ {0, 1, 5} — and for a range of repetitions T ∈ {1, 2, . . . , 30}.