• DOI:10.1137/19m126476x
Corpus ID: 207853305

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

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed