On matrix estimation under monotonicity constraints

Sabyasachi Chatterjee, Adityanand Guntuboyina, Bodhisattva Sen

Research output: Contribution to journalArticlepeer-review


We consider the problem of estimating an unknown n1 × n2 matrix θ from noisy observations under the constraint that θ is nondecreasing in both rows and columns. We consider the least squares estimator (LSE) in this setting and study its risk properties. We show that the worst case risk of the LSE is n-1/2, up to multiplicative logarithmic factors, where n = n1n2 and that the LSE is minimax rate optimal (up to logarithmic factors). We further prove that for some special θ, the risk of the LSE could be much smaller than n-1/2; in fact, it could even be parametric, that is, n-1 up to logarithmic factors. Such parametric rates occur when the number of "rectangular" blocks of θ is bounded from above by a constant. We also derive an interesting adaptation property of the LSE which we term variable adaptation -the LSE adapts to the "intrinsic dimension" of the problem and performs as well as the oracle estimator when estimating a matrix that is constant along each row/column. Our proofs, which borrow ideas from empirical process theory, approximation theory and convex geometry, are of independent interest.

Original languageEnglish (US)
Pages (from-to)1072-1100
Number of pages29
Issue number2
StatePublished - May 2018


  • Adaptation
  • Bivariate isotonic regression
  • Metric entropy bounds
  • Minimax lower bound
  • Oracle inequalities
  • Tangent cone
  • Variable adaptation

ASJC Scopus subject areas

  • Statistics and Probability

Fingerprint Dive into the research topics of 'On matrix estimation under monotonicity constraints'. Together they form a unique fingerprint.

Cite this