Electronic Journal of Statistics

On signal detection and confidence sets for low rank inference problems

Alexandra Carpentier and Richard Nickl

Full-text: Open access

Abstract

We consider the signal detection problem in the Gaussian design trace regression model with low rank alternative hypotheses. We derive the precise (Ingster-type) detection boundary for the Frobenius and the nuclear norm. We then apply these results to show that honest confidence sets for the unknown matrix parameter that adapt to all low rank sub-models in nuclear norm do not exist. This shows that recently obtained positive results in [5] for confidence sets in low rank recovery problems are essentially optimal.

Article information

Source
Electron. J. Statist., Volume 9, Number 2 (2015), 2675-2688.

Dates
Received: July 2015
First available in Project Euclid: 8 December 2015

Permanent link to this document
https://projecteuclid.org/euclid.ejs/1449582159

Digital Object Identifier
doi:10.1214/15-EJS1087

Mathematical Reviews number (MathSciNet)
MR3432430

Zentralblatt MATH identifier
1329.62216

Subjects
Primary: 62G15: Tolerance and confidence regions
Secondary: 62G10: Hypothesis testing

Keywords
Low rank matrices confidence sets signal detection nuclear norm

Citation

Carpentier, Alexandra; Nickl, Richard. On signal detection and confidence sets for low rank inference problems. Electron. J. Statist. 9 (2015), no. 2, 2675--2688. doi:10.1214/15-EJS1087. https://projecteuclid.org/euclid.ejs/1449582159


Export citation

References

  • [1] E. Arias-Castro, E.J. Candès, and Y. Plan. Global testing under sparse alternatives: ANOVA, multiple comparisons and the higher criticism., Ann. Statist., 39 :2533–2556, 2011.
  • [2] A.D. Bull and R. Nickl. Adaptive confidence sets in $L^2$., Probability Theory and Related Fields, 156:889–919, 2013.
  • [3] T.T. Cai and A. Zhang. ROP: matrix recovery via rank-one projections., Ann. Statist., 43(1):102–138, 2015.
  • [4] E.J. Candès and Y. Plan. Tight oracle inequalities for low-rank matrix recovery from a minimal number of noisy random measurements., IEEE Trans. Inform. Theory, 57(4) :2342–2359, 2011.
  • [5] A. Carpentier, J. Eisert, D. Gross, and R. Nickl. Uncertainty Quantification for Matrix Compressed Sensing and Quantum Tomography Problems., arXiv :1504.03234, 2015.
  • [6] E. Giné and R. Nickl., Mathematical foundations of infinite-dimensional statistical models. to appear, Cambridge University Press, 2015.
  • [7] D. Gross, Y.-K. Liu, S.T. Flammia, S. Becker, and J. Eisert. Quantum state tomography via compressed sensing., Phys. Rev. Lett., 105(15) :150401, 2010.
  • [8] M. Hoffmann and R. Nickl. On adaptive inference and confidence bands., Ann. Statist., 39 :2382–2409, 2011.
  • [9] Y.I. Ingster, A.B. Tsybakov, and N. Verzelen. Detection boundary in sparse regression., Elec. J. Stat., 4 :1476–1526, 2010.
  • [10] Y.I. Ingster and I.A. Suslina., Nonparametric goodness-of-fit testing under Gaussian models, volume 169 of Lecture Notes in Statistics. Springer-Verlag, New York, 2003.
  • [11] V. Koltchinskii. Von Neumann entropy penalization and low-rank matrix estimation., Ann. Statist., 39(6) :2936–2973, 2011.
  • [12] V. Koltchinskii, K. Lounici, and A.B. Tsybakov. Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion., Ann. Statist., 39(5) :2302–2329, 2011.
  • [13] S. Negahban and M.J. Wainwright. Estimation of (near) low-rank matrices with noise and high-dimensional scaling., The Annals of Statistics, 39 :1069–1097, 2011.
  • [14] R. Nickl and S. van de Geer. Confidence sets in sparse regression., Ann. Statist., 41(6) :2852–2876, 2013.