Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality

Changxiao Cai, H. Vincent Poor, Yuxin Chen

Research output: Contribution to journalArticlepeer-review


We study the distribution and uncertainty of nonconvex optimization for noisy tensor completion&#x2014;the problem of estimating a low-rank tensor given incomplete and corrupted observations of its entries. Focusing on a two-stage estimation algorithm proposed by [2], we characterize the distribution of this nonconvex estimator down to fine scales. This distributional theory in turn allows one to construct valid and short confidence intervals for both the unseen tensor entries and the unknown tensor factors. The proposed inferential procedure enjoys several important features: (1) it is fully adaptive to noise heteroscedasticity, and (2) it is data-driven and automatically adapts to unknown noise distributions. Furthermore, our findings unveil the statistical optimality of nonconvex tensor completion: it attains un-improvable <italic>l</italic>2 accuracy&#x2014;including both the rates and the pre-constants&#x2014;when estimating both the unknown tensor and the underlying tensor factors.

Original languageEnglish (US)
Pages (from-to)1
Number of pages1
JournalIEEE Transactions on Information Theory
StateAccepted/In press - 2022

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences


  • confidence intervals
  • Estimation
  • heteroscedasticity
  • Image reconstruction
  • Indexes
  • Noise measurement
  • nonconvex optimization
  • Optimization
  • tensor completion
  • Tensors
  • Uncertainty
  • uncertainty quantification


Dive into the research topics of 'Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality'. Together they form a unique fingerprint.

Cite this