A Lower Bound for the Fisher Information Measure

Abstract

The problem how to approximately determine the absolute value of the Fisher information measure for a general parametric probabilistic system is considered. Having available the first and second moment of the system output in a parametric form, it is shown that the information measure can be bounded from below through a replacement of the original system by a Gaussian system with equivalent moments. The presented technique is applied to a system of practical importance and the potential quality of the bound is demonstrated.

4 pages, submitted to IEEE Signal Processing Letters

References in corpus (1)

• Gaussian Assumption: the Least Favorable but the Most Useful

Cited by in corpus (17)

• Far-field Superresolution of Thermal Electromagnetic Sources at the Quantum Limit
• Subdiffraction incoherent optical imaging via spatial-mode demultiplexing
• Multiparameter squeezing for optimal quantum enhancements in sensor networks
• Quantum limits of superresolution in a noisy environment
• A quantitative comparison of amplitude versus intensity interferometry for astronomy
• Cramer-Rao bound analog of Bayes rule
• A Pessimistic Approximation for the Fisher Information Measure
• One-bit LFMCW Radar: Spectrum Analysis and Target Detection
• Measurement-driven Quality Assessment of Nonlinear Systems by Exponential Replacement
• Quantum Information Measures in Quartic and Symmetric Potentials using perturbative approach
• Study of Channel Estimation with Oversampling for 1-bit Large-Scale MIMO Systems
• Fisher information flow in artificial neural networks
• Taking a Lesson from Quantum Particles for Statistical Data Privacy
• Study of Channel Estimation Algorithms for Large-Scale Multiple-Antenna Systems using 1-Bit ADCs and Oversampling
• Comments on "Overdemodulation for High-Performance Receivers with Low-Resolution ADC"
• Overdemodulation for High-Performance Receivers with Low-Resolution ADC
• Investigation of Channel Estimation Techniques with 1-bit Quantization and Oversampling for Multiple-Antenna Systems