Corpus ID: 207852417

Online matrix factorization for Markovian data and applications to Network Dictionary Learning

@article{Lyu2019OnlineMF,
  title={Online matrix factorization for Markovian data and applications to Network Dictionary Learning},
  author={Hanbaek Lyu and D. Needell and Laura Balzano},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.01931}
}
  • Hanbaek Lyu, D. Needell, Laura Balzano
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Online Matrix Factorization (OMF) is a fundamental tool for dictionary learning problems, giving an approximate representation of complex data sets in terms of a reduced number of extracted features. Convergence guarantees for most of the OMF algorithms in the literature assume independence between data matrices, and the case of a dependent data stream remains largely unexplored. In this paper, we show that the well-known OMF algorithm for i.i.d. stream of data proposed in \cite… CONTINUE READING
    7 Citations
    Applications of Online Nonnegative Matrix Factorization to Image and Time-Series Data
    • 1
    • PDF
    COVID-19 Time-series Prediction by Joint Dictionary Learning and Online NMF
    • 1
    • PDF
    Learning low-rank latent mesoscale structures in networks
    • 2
    • PDF
    On Nonnegative Matrix and Tensor Decompositions for COVID-19 Twitter Dynamics
    • 2
    • PDF

    References

    SHOWING 1-10 OF 79 REFERENCES
    Online Learning for Matrix Factorization and Sparse Coding
    • 2,336
    • PDF
    Online Nonnegative Matrix Factorization with General Divergences
    • 20
    • PDF
    Online Convex Matrix Factorization with Representative Regions
    • 2
    • PDF
    NOODL: Provable Online Dictionary Learning and Sparse Coding
    • 8
    • PDF
    Online Nonnegative Matrix Factorization With Robust Stochastic Approximation
    • 256
    Stochastic Subsampling for Factorizing Huge Matrices
    • 21
    • PDF
    Semi-Supervised Nonnegative Matrix Factorization
    • 171
    The Why and How of Nonnegative Matrix Factorization
    • N. Gillis
    • Mathematics, Computer Science
    • ArXiv
    • 2014
    • 254
    • PDF