Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Intrinsic Bayesian Cramér-Rao Bound with an Application to Covariance Matrix Estimation (2311.04748v3)

Published 8 Nov 2023 in math.ST, cs.LG, stat.AP, stat.ML, and stat.TH

Abstract: This paper presents a new performance bound for estimation problems where the parameter to estimate lies in a Riemannian manifold (a smooth manifold endowed with a Riemannian metric) and follows a given prior distribution. In this setup, the chosen Riemannian metric induces a geometry for the parameter manifold, as well as an intrinsic notion of the estimation error measure. Performance bound for such error measure were previously obtained in the non-Bayesian case (when the unknown parameter is assumed to deterministic), and referred to as \textit{intrinsic} Cram\'er-Rao bound. The presented result then appears either as: \textit{a}) an extension of the intrinsic Cram\'er-Rao bound to the Bayesian estimation framework; \textit{b}) a generalization of the Van-Trees inequality (Bayesian Cram\'er-Rao bound) that accounts for the aforementioned geometric structures. In a second part, we leverage this formalism to study the problem of covariance matrix estimation when the data follow a Gaussian distribution, and whose covariance matrix is drawn from an inverse Wishart distribution. Performance bounds for this problem are obtained for both the mean squared error (Euclidean metric) and the natural Riemannian distance for Hermitian positive definite matrices (affine invariant metric). Numerical simulation illustrate that assessing the error with the affine invariant metric is revealing of interesting properties of the maximum a posteriori and minimum mean square error estimator, which are not observed when using the Euclidean metric.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. H. Cramér, Mathematical Methods of Statistics, New York: Princeton University, 1946.
  2. C. Radhakrishna Rao, Information and the Accuracy Attainable in the Estimation of Statistical Parameters, pp. 235–247, Springer New York, New York, NY, 1992.
  3. A. Bhattacharyya, “On some analogues of the amount of information and their use in statistical estimation,” Sankhya: The Indian Journal of Statistics (1933-1960), vol. 8, no. 1, pp. 1–14, 1946.
  4. E. W. Barankin, “Locally Best Unbiased Estimates,” The Annals of Mathematical Statistics, vol. 20, no. 4, pp. 477 – 501, 1949.
  5. “General classes of performance lower bounds for parameter estimation—part ii: Bayesian bounds,” IEEE Transactions on Information Theory, vol. 56, no. 10, pp. 5064–5082, 2010.
  6. “A new barankin bound approximation for the prediction of the threshold region performance of maximum likelihood estimators,” IEEE Transactions on Signal Processing, vol. 56, no. 11, pp. 5319–5333, 2008.
  7. “Cyclic barankin-type bounds for non-bayesian periodic parameter estimation,” IEEE Transactions on Signal Processing, vol. 62, no. 13, pp. 3321–3336, 2014.
  8. H.L. Van Trees, Estimation and modulation theory, vol. 1, John Wiley and Sons, 2001.
  9. Bayesian Bounds for Parameter Estimation and Nonlinear Filtering/Tracking, John Wiley and Sons, 2007.
  10. E. Weinstein and A. J. Weiss, “A general class of lower bounds in parameter estimation,” IEEE Trans. Inform. Theory, vol. 34, pp. 338–342, 1988.
  11. “A class of weiss–weinstein bounds and its relationship with the bobrovsky–mayer-wolf–zakaï bounds,” IEEE Transactions on Information Theory, vol. 63, no. 4, pp. 2226–2240, 2017.
  12. “Lower bounds for parametric estimation with constraints,” IEEE Transactions on Information Theory, vol. 36, no. 6, pp. 1285–1301, 1990.
  13. “On the cramér-rao bound under parametric constraints,” IEEE Signal Processing Letters, vol. 5, no. 7, pp. 177–179, 1998.
  14. Thomas L Marzetta, “A simple derivation of the constrained multiple parameter cramer-rao bound,” IEEE Transactions on Signal Processing, vol. 41, no. 6, pp. 2247–2249, 1993.
  15. “On the constrained cramér–rao bound with a singular fisher information matrix,” IEEE Signal Processing Letters, vol. 16, no. 6, pp. 453–456, 2009.
  16. A Al-Sharadqah and KC Ho, “Constrained cramér–rao lower bound in errors-in variables (eiv) models: Revisited,” Statistics & Probability Letters, vol. 135, pp. 118–126, 2018.
  17. “Cramér–rao bound for constrained parameter estimation using lehmann-unbiasedness,” IEEE Transactions on Signal Processing, vol. 67, no. 3, pp. 753–768, 2018.
  18. “Cramér-rao bound under norm constraint,” IEEE Signal Processing Letters, vol. 26, no. 9, pp. 1393–1397, 2019.
  19. “A constrained hybrid cramér-rao bound for parameter estimation,” in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2015, pp. 3472–3476.
  20. “Barankin-type bound for constrained parameter estimation,” IEEE Transactions on Signal Processing, 2023.
  21. “Constrained posterior cramér-rao bound for discrete-time systems,” IFAC-PapersOnLine, vol. 50, no. 1, pp. 3768–3773, 2017.
  22. “On cramér-rao lower bounds with random equality constraints,” in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020, pp. 5355–5359.
  23. Harrie Hendriks, “A cramér-rao type lower bound for estimators with values in a manifold,” Journal of Multivariate Analysis, vol. 38, no. 2, pp. 245–261, 1991.
  24. Steven T. Smith, “Covariance, subspace, and intrinsic Cramér-Rao bounds,” IEEE Transactions on Signal Processing, vol. 53, no. 5, pp. 1610–1630, 2005.
  25. J. Xavier and V. Barroso, “Intrinsic variance lower bound (ivlb): an extension of the cramer-rao bound to riemannian manifolds,” in Proceedings. (ICASSP ’05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., 2005, vol. 5, pp. v/1033–v/1036 Vol. 5.
  26. “A note on the intrinsic cramer-rao bound,” in International Conference on Geometric Science of Information. Springer, 2013, pp. 377–386.
  27. Nicolas Boumal, “On intrinsic cramér-rao bounds for riemannian submanifolds and quotient manifolds,” IEEE transactions on signal processing, vol. 61, no. 7, pp. 1809–1821, 2013.
  28. “Cramér–rao bounds for synchronization of rotations,” Information and Inference: A Journal of the IMA, vol. 3, no. 1, pp. 1–39, 2014.
  29. Nicolas Boumal, Optimization and estimation on manifolds, Ph.D. thesis, Université catholique de Louvain, feb 2014.
  30. S. Bonnabel and A. Barrau, “An intrinsic cramér-rao bound on lie groups,” in International Conference on Networked Geometric Science of Information, 2015, pp. 664–672.
  31. “Intrinsic cramér–rao bounds for scatter and shape matrices estimation in ces distributions,” IEEE Signal Processing Letters, vol. 26, no. 2, pp. 262–266, 2019.
  32. “On the cramer-rao bound in riemannian manifolds with application to so(3),” in 2020 59th IEEE Conference on Decision and Control (CDC), 2020, pp. 4117–4122.
  33. “An intrinsic mcaulay-seidman bound for parameters evolving on matrix lie groups,” in Proceedings of the 56th Asilomar Conference on Signals, Systems and Computers, 2022.
  34. “A cramer-rao type inequality for random variables in euclidean manifolds,” Sankhya: The Indian Journal of Statistics, Series A (1961-2002), vol. 54, no. 3, pp. 387–401, 1992.
  35. “The fisher-rao geometry of ces distributions,” arXiv preprint arXiv:2310.01032, 2023.
  36. P.E. Jupp, “A van trees inequality for estimators on manifolds,” Journal of Multivariate Analysis, vol. 101, no. 8, pp. 1814–1825, 2010.
  37. “Information geometric approach to bayesian lower error bounds,” 2018.
  38. Methods of information geometry, vol. 191, American Mathematical Soc., 2000.
  39. “An intrinsic bayesian bound for estimators on the lie groups so (3) and se (3),” Signal Processing, vol. 214, pp. 109232, 2024.
  40. “Barankin, mcaulay–seidman and cramér–rao bounds on matrix lie groups,” Automatica, vol. 156, pp. 111199, 2023.
  41. “Modeling covariance matrices in terms of standard deviations and correlations, with application to shrinkage,” Statistica Sinica, pp. 1281–1311, 2000.
  42. Riemannian geometry, Springer, 1990.
  43. S. Lang, Differential and Riemannian manifolds, Springer, 2012.
  44. J. M. Lee, Riemannian manifolds: an introduction to curvature, Springer, 2006.
  45. Optimization algorithms on matrix manifolds, Princeton University Press, 2009.
  46. Nicolas Boumal, An introduction to optimization on smooth manifolds, Cambridge University Press, 2023.
  47. “Riemannian Gaussian distributions on the space of symmetric positive definite matrices,” IEEE Transactions on Information Theory, vol. 63, no. 4, pp. 2153–2170, 2017.
  48. “Bayesian signal subspace estimation with compound gaussian sources,” Signal Processing, vol. 167, pp. 107310, 2020.
  49. “Knowledge-aided bayesian covariance matrix estimation in compound-gaussian clutter,” in 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010, pp. 2574–2577.
  50. Rajendra Bhatia, Positive definite matrices, Princeton university press, 2009.
  51. L. T. Skovgaard, “A Riemannian geometry of the multivariate normal model,” Scandinavian journal of statistics, pp. 211–223, 1984.
  52. D. Maiwald and D. Kraus, “Calculations of moments of complex wishart and inverse whishart distributed matrices,” IEE Proc. Radar Sonar Navig., vol. 147, no. 4, pp. 162–168, August 2000.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets