English

Tensor denoising and completion based on ordinal observations

Machine Learning 2020-12-15 v3 Machine Learning Statistics Theory Methodology Statistics Theory

Abstract

Higher-order tensors arise frequently in applications such as neuroimaging, recommendation system, social network analysis, and psychological studies. We consider the problem of low-rank tensor estimation from possibly incomplete, ordinal-valued observations. Two related problems are studied, one on tensor denoising and the other on tensor completion. We propose a multi-linear cumulative link model, develop a rank-constrained M-estimator, and obtain theoretical accuracy guarantees. Our mean squared error bound enjoys a faster convergence rate than previous results, and we show that the proposed estimator is minimax optimal under the class of low-rank models. Furthermore, the procedure developed serves as an efficient completion method which guarantees consistent recovery of an order-KK (d,,d)(d,\ldots,d)-dimensional low-rank tensor using only O~(Kd)\tilde{\mathcal{O}}(Kd) noisy, quantized observations. We demonstrate the outperformance of our approach over previous methods on the tasks of clustering and collaborative filtering.

Keywords

Cite

@article{arxiv.2002.06524,
  title  = {Tensor denoising and completion based on ordinal observations},
  author = {Chanwoo Lee and Miaoyan Wang},
  journal= {arXiv preprint arXiv:2002.06524},
  year   = {2020}
}

Comments

35 pages, 6 figures

R2 v1 2026-06-23T13:42:59.781Z