Corpus ID: 2598866

Uniqueness of Tensor Decompositions with Applications to Polynomial Identifiability

@inproceedings{Bhaskara2014UniquenessOT,
  title={Uniqueness of Tensor Decompositions with Applications to Polynomial Identifiability},
  author={Aditya Bhaskara and M. Charikar and Aravindan Vijayaraghavan},
  booktitle={COLT},
  year={2014}
}
  • Aditya Bhaskara, M. Charikar, Aravindan Vijayaraghavan
  • Published in COLT 2014
  • Computer Science, Mathematics
  • We give a robust version of the celebrated result of Kruskal on the uniqueness of tensor decompositions: we prove that given a tensor whose decomposition satisfies a robust form of Kruskal's rank condition, it is possible to approximately recover the decomposition if the tensor is known up to a sufficiently small (inverse polynomial) error. Kruskal's theorem has found many applications in proving the identifiability of parameters for various latent variable models and mixture models such as… CONTINUE READING

    Paper Mentions

    Smoothed analysis of tensor decompositions
    103
    An Algorithm For Generic and Low-Rank Specific Identifiability of Complex Tensors
    63
    Iterative Hard Thresholding for Low CP-rank Tensor Models
    1
    Better Agnostic Clustering Via Relaxed Tensor Norms
    27
    Tensor Decompositions via Two-Mode Higher-Order SVD (HOSVD)
    10

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 105 REFERENCES
    Smoothed analysis of tensor decompositions
    103
    Tensor decompositions for learning latent variable models
    761
    Identifiability of parameters in latent structure models with many observed variables
    353
    On Generic Identifiability of 3-Tensors of Small Rank
    105
    Most Tensor Problems Are NP-Hard
    644
    Settling the Polynomial Learnability of Mixtures of Gaussians
    246