Tensors

Blog post: Tensor decompositions in ML by Rong Ge

Tensor decompositions

Surveys

  • Kolda & Bader, 2009: Tensor decompositions and applications (doi)
  • Anandkumar et al, 2014: Tensor decompositions for learning latent variable models (arxiv, pdf)
  • Sidiropoulos et al, 2016: Tensor decomposition for signal processing and ML (arxiv)

Research papers

  • Silva, Lim, 2008: Tensor rank and the ill-posedness of the best low-rank approximation problem (doi, arxiv)
  • Lim, 2005: Singular values and eigenvalues of tensors: a variational approach (doi)
  • Gnang et al, 2010: A spectral theory for tensors (arxiv)
    • Alternative to CP and Tucker decompositions

Statistical aspects

  • Montanari, 2014: A statistical model for tensor PCA (arxiv)
  • Ge et al, 2015: Escaping From Saddle Points — Online Stochastic Gradient for Tensor Decomposition (arxiv)
    • See Wright et al’s “When are nonconvex functions not scary?” for an overview
  • Barak et al, 2015: Dictionary Learning and Tensor Decomposition via the Sum-of-Squares Method (doi)
  • Gross et al, 2016: Improving compressed sensing with the diamond norm (doi, arxiv)
    • Related to 4-tensors