Fundamental bounds for parameter estimation with few measurements
Abstract: Bounding the optimal precision in parameter estimation tasks is of central importance for technological applications. In the regime of a small number of measurements, or that of low signal-to-noise ratios, the meaning of common frequentist bounds such as the Cram\'er-Rao bound (CRB) become questionable. Here, we discuss different linear (Barankin-like) conditions that can be imposed on estimators and analyze when these conditions admit an optimal estimator with finite variance, for any number of measurement repetitions. We show that, if the number of imposed conditions is larger than the number of measurement outcomes, there generally does not exist a corresponding estimator with finite variance. We analyze this result from different viewpoints and examples and elaborate on connections to the shot-noise limit and the Kitaev phase estimation algorithm. We then derive an extended Cram\'er-Rao bound that is compatible with a finite variance in situations where the Barankin bound is undefined. Finally, we show an exemplary numerical confrontation between frequentist and Bayesian approaches to parameter estimation.
- E. L. Lehmann and G. Casella, Theory of Point Estimation (Springer New York, NY, 2006).
- R. A. Fisher and E. J. Russell, On the mathematical foundations of theoretical statistics, Philos. Trans. R. Soc. A 222, 309 (1922).
- H. Cramér, Mathematical Methods of Statistics (Princeton Univ. Press, 1946).
- C. R. Rao, Information and the accuracy attainable in the estimation of statistical parameters, Bull. Calcutta Math. Soc. 37, 81 (1945).
- C. W. Helstrom, Quantum detection and estimation theory, J. Stat. Phys. 1, 231 (1969).
- A. S. Holevo, Probabilistic and Statistical Aspects of Quantum Theory (North-Holland, Amsterdam, 1982).
- M. G. A. Paris, Quantum estimation for quantum technology, Int. J. Quantum Inf. 07, 125 (2009).
- G. Tóth and I. Apellaniz, Quantum metrology from a quantum information science perspective, J. Phys. A 47, 424006 (2014).
- A. Bhattacharyya, On Some Analogues of the Amount of Information and Their Use in Statistical Estimation, Sankhya 8, 1 (1946).
- E. W. Barankin, Locally Best Unbiased Estimates, Ann. Math. Stat. 20, 477 (1949).
- J. M. Hammersley, On Estimating Restricted Parameters, J. R. Stat. Soc. Series B Stat. Methodol. 12, 192 (1950).
- D. G. Chapman and H. Robbins, Minimum Variance Estimation Without Regularity Assumptions, Ann. Math. Stat. 22, 581 (1951).
- J. Abel, A bound on mean-square-estimate error, IEEE Trans. Inf. Theory 39, 1675 (1993).
- M. Gessner and A. Smerzi, Hierarchies of Frequentist Bounds for Quantum Metrology: From Cramér-Rao to Barankin, Phys. Rev. Lett. 130, 260801 (2023).
- R. McAulay and L. Seidman, A useful form of the Barankin lower bound and its application to PPM threshold analysis, IEEE Trans. Inf. Theory 15, 273 (1969).
- R. McAulay and E. Hofstetter, Barankin Bounds on Parameter Estimation, IEEE Trans. Inf. Theory 17, 669 (1971).
- L. Knockaert, The Barankin bound and threshold behavior in frequency estimation, IEEE Trans. Signal Process. 45, 2398 (1997).
- T. Marzetta, A simple derivation of the constrained multiple parameter Cramer-Rao bound, IEEE Trans. Signal Process. 41, 2247 (1993).
- A. Y. Kitaev, Quantum measurements and the Abelian Stabilizer Problem (1995), arXiv:quant-ph/9511026 [quant-ph] .
- A. Hájek, in The Stanford Encyclopedia of Philosophy, edited by E. N. Zalta and U. Nodelman (Metaphysics Research Lab, Stanford University, 2023) Winter 2023 ed.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.