A posteriori error bounds for joint matrix decomposition problems

Authors: Nicolo Colombo, Nikos Vlassis

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

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the bound on synthetic data for which the ground truth is known.
Researcher Affiliation Collaboration Nicolò Colombo Department of Statistical Science University College London nicolo.colombo@ucl.ac.uk Nikos Vlassis Adobe Research San Jose, CA vlassis@adobe.com
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not contain any statements about releasing source code or links to a code repository.
Open Datasets No The paper states 'We created a set of synthetic problems in which the ground truth is known'. This indicates generated data, not a publicly available dataset with access information.
Dataset Splits No The paper evaluates an error bound using synthetic data and different algorithms, but it does not specify traditional train/validation/test dataset splits for model training or evaluation, as the experiment is not about training a machine learning model.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments.
Software Dependencies No The paper mentions using 'Gauss-Newton algorithm [8]' and 'Jacobi algorithm [13] (our implementation)' but does not provide specific software versions for these or any other dependencies.
Experiment Setup Yes For each set Mσ = { M̂n}N n=1, two approximate joint triangularizers were computed by optimizing (4) using two different iterative algorithms, the Gauss-Newton algorithm [8], and the Jacobi algorithm [13] (our implementation), initialized with the same random orthogonal matrix. ... We considered two settings, N = 5 and N = 100, and several different noise levels obtained by varying the perturbation parameter σ.