Robust Low-Tubal-Rank Tensor Completion via Convex Optimization

Authors: Qiang Jiang, Michael Ng

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments verify our theoretical results and realworld applications demonstrate the effectiveness of our algorithm. We conduct a series of experiments to demonstrate the validity of our theorem, and show possible applications of our model and algorithm.
Researcher Affiliation Academia Qiang Jiang and Michael Ng Department of Mathematics, The University of Hong Kong, Hong Kong michaelkwokpong@gmail.com This work was conducted when the authors were with the Department of Mathematics, Hong Kong Baptist University.
Pseudocode No The paper mentions using the ADMM algorithm and refers to algorithms from other papers, but it does not provide its own pseudocode or algorithm block.
Open Source Code No The paper does not contain any explicit statement or link providing access to the open-source code for the methodology described.
Open Datasets Yes We download 50 color images at random from the Berkeley Segmentation Database (BSD) [Martin et al., 2001].
Dataset Splits No The paper describes how data is generated and corrupted, and how observations are chosen (e.g., 'randomly choose a percentage ρ of the noisy tensor entries'), but it does not specify explicit training, validation, or test dataset splits or percentages.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions using 'MATLAB command fft' and the 'ADMM algorithm', and compares against other methods like 'BM3D' and 'Ha LRTC', but it does not provide specific version numbers for any software or libraries used in its implementation or experiments.
Experiment Setup No The paper specifies parameters for data generation (e.g., tubal rank 'r', percentage of observed entries 'ρ', proportion of gross corruptions 'γ') and the penalty parameter 'λ = 1/ ρn(1)n3'. It also states using a 'standard alternating direction method of multipliers (ADMM) algorithm' but does not provide specific hyperparameters or system-level training settings for ADMM or any other part of the experimental setup.