Online Convex Matrix Factorization with Representative Regions

Authors: Jianhao Peng, Olgica Milenkovic, Abhishek Agarwal

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on synthetic and real world datasets show significant computational savings of the proposed online convex MF method compared to classical convex MF.
Researcher Affiliation Academia Abhishek Agarwal Electrical and Computer Engineering University of Illinois Urbana-Champaign abhiag@illinois.edu Jianhao Peng Electrical and Computer Engineering University of Illinois Urbana-Champaign jianhao2@illinois.edu Olgica Milenkovic Electrical and Computer Engineering University of Illinois Urbana-Champaign milenkov@illinois.edu
Pseudocode Yes Algorithm 1 Initialization; Algorithm 2 Online cvx MF
Open Source Code No The paper does not provide any specific links or explicit statements about the availability of its source code.
Open Datasets Yes The real world datasets include are taken from the UCI Machine Learning [30] and the 10X Genomics repository [31].
Dataset Splits Yes After performing cross validation on an evaluation set of size 1000, we selected c= 0.2.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments. It only discusses the datasets and algorithms.
Software Dependencies No The paper does not list specific software dependencies with version numbers, such as programming languages, libraries, or frameworks used for implementation.
Experiment Setup Yes After performing cross validation on an evaluation set of size 1000, we selected c= 0.2. ... All algorithms ran 3,000 iterations with N=150 and λ=0.1 to generate eigenimages, capturing the characteristic features used as bases [35].