Normalized Spectral Map Synchronization

Authors: Yanyao Shen, Qixing Huang, Nati Srebro, Sujay Sanghavi

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

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the usefulness of Norm Spec Sync on both synthetic and real datasets.
Researcher Affiliation Academia Yanyao Shen UT Austin Austin, TX 78712 shenyanyao@utexas.edu Qixing Huang TTI Chicago and UT Austin Austin, TX 78712 huangqx@cs.utexas.edu Nathan Srebro TTI Chicago Chicago, IL 60637 nati@ttic.edu Sujay Sanghavi UT Austin Austin, TX 78712 sanghavi@mail.utexas.edu
Pseudocode Yes Algorithm 1 Norm Spec Sync Input: Xobs based on (1), δmax Initialize W0: set W0 as an initial guess for the top-m orthonormal eigenvectors, k 0 while W (k) W (k 1) > δmax do W (k+1)+ = Xobs W (k), W (k+1)R(k+1) = W (k+1)+, (QR factorization), k k + 1. end while Set W = W (k) and X spec i1 = (WW T )i1. Round each X spec i1 into the corresponding Xi1 by solving (3). Output: Xij = XT j1Xi1, 1 i, j n.
Open Source Code No The paper does not provide an explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We first evaluate Norm Spec Sync on CMU Hotel and CMU House datasets [20].
Dataset Splits No The paper mentions generating synthetic data and using CMU Hotel/House and SCAPE datasets, but does not provide specific details on how these datasets were split into training, validation, or test sets (e.g., percentages, sample counts, or cross-validation folds).
Hardware Specification No The paper reports computation times (e.g., 'The averaged running time for Spec Sync is 2.25 second') but does not specify the hardware components (e.g., CPU, GPU models, or memory) used for these experiments.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies, libraries, or programming languages used in the experiments.
Experiment Setup No The paper describes the algorithm and general experimental procedures, but it does not provide specific details on the experimental setup, such as hyperparameter values (e.g., learning rate, batch size) or other training configuration settings.