ISLET: Fast and Optimal Low-rank Tensor Regression via Importance Sketching

@article{Zhang2020ISLETFA,
  title={ISLET: Fast and Optimal Low-rank Tensor Regression via Importance Sketching},
  author={Anru Zhang and Yuetian Luo and G. Raskutti and M. Yuan},
  journal={SIAM J. Math. Data Sci.},
  year={2020},
  volume={2},
  pages={444-479}
}
  • Anru Zhang, Yuetian Luo, +1 author M. Yuan
  • Published 2020
  • Mathematics, Computer Science
  • SIAM J. Math. Data Sci.
  • In this paper, we develop a novel procedure for low-rank tensor regression, namely \emph{\underline{I}mportance \underline{S}ketching \underline{L}ow-rank \underline{E}stimation for \underline{T}ensors} (ISLET). The central idea behind ISLET is \emph{importance sketching}, i.e., carefully designed sketches based on both the responses and low-dimensional structure of the parameter of interest. We show that the proposed method is sharply minimax optimal in terms of the mean-squared error under… CONTINUE READING
    10 Citations
    Sparse and Low-Rank Tensor Estimation via Cubic Sketchings
    • 22
    • PDF
    Inference for Low-rank Tensors - No Need to Debias
    • PDF
    Practical Leverage-Based Sampling for Low-Rank Tensor Decomposition
    • 3
    • PDF
    An Optimal Statistical and Computational Framework for Generalized Tensor Estimation
    • 7
    • PDF
    CP Degeneracy in Tensor Regression
    • PDF
    Tensor Clustering with Planted Structures: Statistical Optimality and Computational Limits
    • 9
    • PDF
    Spectral Methods for Data Science: A Statistical Perspective
    • 1
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 151 REFERENCES
    Sparse and Low-Rank Tensor Estimation via Cubic Sketchings
    • 22
    • PDF
    Spectral algorithms for tensor completion
    • 44
    • PDF
    Sharper Bounds for Regularized Data Fitting
    • 26
    • PDF
    Robust Low-Rank Matrix Recovery
    • 21
    Statistically Optimal and Computationally Efficient Low Rank Tensor Completion from Noisy Entries
    • 23
    • PDF
    Sharper Bounds for Regression and Low-Rank Approximation with Regularization
    • 11
    • PDF
    Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery
    • 217
    • Highly Influential
    • PDF
    Convex Regularization for High-Dimensional Multi-Response Tensor Regression
    • 32
    • PDF
    Fast and Guaranteed Tensor Decomposition via Sketching
    • 81
    • PDF