The Annals of Statistics

Von Neumann entropy penalization and low-rank matrix estimation

Vladimir Koltchinskii

Full-text: Open access

Abstract

We study a problem of estimation of a Hermitian nonnegatively definite matrix ρ of unit trace (e.g., a density matrix of a quantum system) based on n i.i.d. measurements (X1, Y1), …, (Xn, Yn), where

Yj = tr(ρXj) + ξj,  j = 1, …, n,

{Xj} being random i.i.d. Hermitian matrices and {ξj} being i.i.d. random variables with ${\mathbb{E}}(\xi_{j}|X_{j})=0$. The estimator

\[\hat{\rho}^{\varepsilon }:=\mathop{\arg\min}_{S\in{\mathcal{S}}}\Biggl[n^{-1}\sum_{j=1}^{n}\bigl(Y_{j}-\operatorname{tr}(SX_{j})\bigr)^{2}+\varepsilon \operatorname{tr}(S\log S)\Biggr]\]

is considered, where ${\mathcal{S}}$ is the set of all nonnegatively definite Hermitian m × m matrices of trace 1. The goal is to derive oracle inequalities showing how the estimation error depends on the accuracy of approximation of the unknown state ρ by low-rank matrices.

Article information

Source
Ann. Statist., Volume 39, Number 6 (2011), 2936-2973.

Dates
First available in Project Euclid: 24 January 2012

Permanent link to this document
https://projecteuclid.org/euclid.aos/1327413774

Digital Object Identifier
doi:10.1214/11-AOS926

Mathematical Reviews number (MathSciNet)
MR3012397

Zentralblatt MATH identifier
1246.62138

Subjects
Primary: 62J99: None of the above, but in this section 62H12: Estimation 60B20: Random matrices (probabilistic aspects; for algebraic aspects see 15B52) 60G15: Gaussian processes 81Q99: None of the above, but in this section

Keywords
Low-rank matrix estimation von Neumann entropy matrix regression empirical processes noncommutative Bernstein inequality quantum state tomography Pauli basis

Citation

Koltchinskii, Vladimir. Von Neumann entropy penalization and low-rank matrix estimation. Ann. Statist. 39 (2011), no. 6, 2936--2973. doi:10.1214/11-AOS926. https://projecteuclid.org/euclid.aos/1327413774


Export citation

References

  • Adamczak, R. (2008). A tail inequality for suprema of unbounded empirical processes with applications to Markov chains. Electron. J. Probab. 13 1000–1034.
  • Ahlswede, R. and Winter, A. (2002). Strong converse for identification via quantum channels. IEEE Trans. Inform. Theory 48 569–579.
  • Artiles, L. M., Gill, R. D. and Guţă, M. I. (2005). An invitation to quantum tomography. J. R. Stat. Soc. Ser. B Stat. Methodol. 67 109–134.
  • Aubrun, G. (2009). On almost randomizing channels with a short Kraus decomposition. Comm. Math. Phys. 288 1103–1116.
  • Bhatia, R. (1997). Matrix Analysis. Graduate Texts in Mathematics 169. Springer, New York.
  • Candès, E. J. and Plan, Y. (2011). Tight oracle bounds for low-rank matrix recovery from a minimal number of random measurements. IEEE Trans. Inform. Theory 57 2342–2359.
  • Candès, E. J. and Recht, B. (2009). Exact matrix completion via convex optimization. Found. Comput. Math. 9 717–772.
  • Candès, E. J. and Tao, T. (2010). The power of convex relaxation: Near-optimal matrix completion. IEEE Trans. Inform. Theory 56 2053–2080.
  • Gross, D. (2011). Recovering low-rank matrices from few coefficients in any basis. IEEE Trans. Inform. Theory 57 1548–1566.
  • Gross, D., Liu, Y. K., Flammia, S. T., Becker, S. and Eisert, J. (2010). Quantum state tomography via compressed sensing. Phys. Rev. Lett. 105 150401.
  • Guédon, O., Mendelson, S., Pajor, A. and Tomczak-Jaegermann, N. (2008). Majorizing measures and proportional subsets of bounded orthonormal systems. Rev. Mat. Iberoam. 24 1075–1095.
  • Klartag, B. and Mendelson, S. (2005). Empirical processes and random projections. J. Funct. Anal. 225 229–245.
  • Klauck, H., Nayak, A., Ta-Shma, A. and Zuckerman, D. (2007). Interaction in quantum communication. IEEE Trans. Inform. Theory 53 1970–1982.
  • Koltchinskii, V. (2009). Sparse recovery in convex hulls via entropy penalization. Ann. Statist. 37 1332–1359.
  • Koltchinskii, V. (2011). Oracle Inequalities in Empirical Risk Minimization and Sparse Recovery Problems. Lecture Notes in Math. 2033. Springer, Heidelberg.
  • Koltchinskii, V., Lounici, K. and Tsybakov, A. (2011). Nuclear norm penalization and optimal rates for noisy low rank matrix completion. Ann. Statist. 39 2302–2329.
  • Ledoux, M. and Talagrand, M. (1991). Probability in Banach Spaces: Isoperimetry and Processes. Ergebnisse der Mathematik und Ihrer Grenzgebiete (3) [Results in Mathematics and Related Areas (3)] 23. Springer, Berlin.
  • Mendelson, S. (2010). Empirical processes with a bounded ψ1 diameter. Geom. Funct. Anal. 20 988–1027.
  • Negahban, S. and Wainwright, M. J. (2010). Restricted strong convexity and weighted matrix completion: Optimal bounds with noise. Available at arXiv:1009.2118.
  • Nielsen, M. A. and Chuang, I. L. (2000). Quantum Computation and Quantum Information. Cambridge Univ. Press, Cambridge.
  • Oliveira, R. I. (2010). Sums of random Hermitian matrices and an inequality by Rudelson. Electron. Commun. Probab. 15 203–212.
  • Recht, B. (2011). A simpler approach to matrix completion. J. Mach. Learn. Res. To appear.
  • Rohde, A. and Tsybakov, A. B. (2011). Estimation of high-dimensional low-rank matrices. Ann. Statist. 39 887–930.
  • Rudelson, M. and Vershynin, R. (2010). Non-asymptotic theory of random matrices: Extreme singular values. In Proceedings of the International Congress of Mathematicians. Hyderabad, India.
  • Simon, B. (1979). Trace Ideals and Their Applications. London Mathematical Society Lecture Note Series 35. Cambridge Univ. Press, Cambridge.
  • Talagrand, M. (2005). The Generic Chaining: Upper and Lower Bounds of Stochastic Processes. Springer, Berlin.
  • Tropp, J. A. (2011). User-friendly tail bounds for sums of random matrices. Found. Comput. Math. To appear.
  • van der Vaart, A. W. and Wellner, J. A. (1996). Weak Convergence and Empirical Processes: With Applications to Statistics. Springer, New York.