On the existence of unbiased resilient estimators in discrete quantum systems

• URL: http://arxiv.org/abs/2402.15242v2
• Date: Fri, 1 Mar 2024 08:33:14 GMT
• Title: On the existence of unbiased resilient estimators in discrete quantum systems
• Authors: Javier Navarro, Ricard Ravell Rodr\'iguez, and Mikel Sanz
• Abstract summary: We compare the performance of Cram'er-Rao and Bhattacharyya bounds when faced with less-than-ideal prior knowledge of the parameter. For a given system dimension, one can construct estimators in quantum systems that exhibit increased robustness to prior ignorance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cram\'er-Rao constitutes a crucial lower bound for the mean squared error of an estimator in frequentist parameter estimation, albeit paradoxically demanding highly accurate prior knowledge of the parameter to be estimated. Indeed, this information is needed to construct the optimal unbiased estimator, which is highly dependent on the parameter. Conversely, Bhattacharyya bounds result in a more resilient estimation about prior accuracy by imposing additional constraints on the estimator. Initially, we conduct a quantitative comparison of the performance between Cram\'er-Rao and Bhattacharyya bounds when faced with less-than-ideal prior knowledge of the parameter. Furthermore, we demonstrate that the $n^{th}$order classical and quantum Bhattacharyya bounds cannot be computed -- given the absence of estimators satisfying the constraints -- under specific conditions tied to the dimension $m$ of the discrete system. Intriguingly, for a system with the same dimension $m$, the maximum non-trivial order $n$ is $m-1$ in the classical case, while in the quantum realm, it extends to $m(m+1)/2-1$. Consequently, for a given system dimension, one can construct estimators in quantum systems that exhibit increased robustness to prior ignorance.

Related papers

• Bayesian and frequentist estimators for the transition frequency of a driven two-level quantum system [0.0]
  We employ both Bayesian and frequentist approaches to estimate the unknown transition frequency. In the frequentist approach, we have shown that reducing the distance between the classical and the quantum Fisher information does not necessarily mean that the estimators as functions of the data deliver an estimate with desirable precision.
  arXiv  Detail & Related papers  (2024-11-15T13:58:52Z)
• Multivariate root-n-consistent smoothing parameter free matching estimators and estimators of inverse density weighted expectations [51.000851088730684]
  We develop novel modifications of nearest-neighbor and matching estimators which converge at the parametric $sqrt n $-rate. We stress that our estimators do not involve nonparametric function estimators and in particular do not rely on sample-size dependent parameters smoothing.
  arXiv  Detail & Related papers  (2024-07-11T13:28:34Z)
• Fundamental bounds for parameter estimation with few measurements [0.0]
  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. 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 derive an extended Cram'er-Rao bound that is compatible with a finite variance in situations where the Barankin bound is undefined.
  arXiv  Detail & Related papers  (2024-02-22T12:40:08Z)
• Intrinsic Bayesian Cramér-Rao Bound with an Application to Covariance Matrix Estimation [49.67011673289242]
  This paper presents a new performance bound for estimation problems where the parameter to estimate lies in a smooth manifold. It induces a geometry for the parameter manifold, as well as an intrinsic notion of the estimation error measure.
  arXiv  Detail & Related papers  (2023-11-08T15:17:13Z)
• Evaluating the quantum optimal biased bound in a unitary evolution process [12.995137315679923]
  We introduce two effective error bounds for biased estimators based on a unitary evolution process. We show their estimation performance by two specific examples of the unitary evolution process.
  arXiv  Detail & Related papers  (2023-09-09T02:15:37Z)
• Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency [53.90687548731265]
  We study optimal procedures for estimating a linear functional based on observational data. For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
  arXiv  Detail & Related papers  (2023-01-16T02:57:37Z)
• Efficient learning of hidden state LTI state space models of unknown order [0.7614628596146599]
  We address two related estimation problems arising in the setup of hidden state linear time invariant (LTI) state space systems. Namely, the estimation of any finite number of the system's Markov parameters and the estimation of a minimal realization for the system. For both problems, we provide statistical guarantees in the form of various estimation error upper bounds, $rank$ recovery conditions, and sample complexity estimates.
  arXiv  Detail & Related papers  (2022-02-03T14:59:13Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Nonparametric Estimation of the Fisher Information and Its Applications [82.00720226775964]
  This paper considers the problem of estimation of the Fisher information for location from a random sample of size $n$. An estimator proposed by Bhattacharya is revisited and improved convergence rates are derived. A new estimator, termed a clipped estimator, is proposed.
  arXiv  Detail & Related papers  (2020-05-07T17:21:56Z)
• Uncertainty and Trade-offs in Quantum Multiparameter Estimation [0.0]
  Uncertainty relations in quantum mechanics express bounds on our ability to simultaneously obtain knowledge about expectation values of non-commuting observables of a quantum system. They quantify trade-offs in accuracy between complementary pieces of information about the system. An uncertainty relation emerges between achievable variances of the different estimators.
  arXiv  Detail & Related papers  (2020-02-14T10:43:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.