ROUTE: Robust Outlier Estimation for Low Rank Matrix Recovery

Authors: Xiaojie Guo, Zhouchen Lin

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Theoretical analysis on convergence and optimality, and experimental results on both synthetic and real data are provided to demonstrate the efficacy of our proposed method and show its superiority over other state-of-the-arts.
Researcher Affiliation Academia State Key Laboratory of Information Security, IIE, Chinese Academy of Sciences University of Chinese Academy of Sciences Key Laboratory of Machine Perception (MOE), School of EECS, Peking University Cooperative Medianet Innovation Center, Shanghai Jiao Tong University
Pseudocode Yes Algorithm 1: ROUTE-LRMR: Solver to Eq.(5)
Open Source Code No The paper does not provide explicit links or statements regarding the open-source availability of the code for ROUTE-LRMR.
Open Datasets Yes The cropped Extended Yale B-10 sequence, containing 64 faces of one subject with size 192 168, is adopted as the dataset. The light imbalance including shadows and highlights on the face significantly breaks the low-rank structure (please see the 1st column in Fig. 3 for example). In this part, we set the guess rank r to 5 for all the competitors. [Hayakawa, 1994]
Dataset Splits No The paper describes how synthetic data is generated and corrupted, and uses the Extended Yale B-10 sequence, but it does not specify explicit train/validation/test dataset splits with percentages or counts for either.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory, or processor types) used for running the experiments.
Software Dependencies No The paper does not specify software dependencies (e.g., library or solver names) with version numbers that would be needed to replicate the experiment.
Experiment Setup Yes The other two parameters α and β are empirically set to 50 and 1 throughout this paper. For the rest experiments unless stated otherwise, we set γ = 0.01. Init.: µ(0) 1 and ρ 1.1; W(0) Rm n Ω 1; L(0) Rm n, U(0) Rm r and V(0) Rr n are all initialized randomly; Z(0) Rm n 0; t 0. In all our experiments, the tolerance factor ς is chosen as 1e 7.