Analysis of Mismatched Estimation Errors Using Gradients of Partition Functions
arXiv:1306.0094
Abstract
We consider the problem of signal estimation (denoising) from a statistical-mechanical perspective, in continuation to a recent work on the analysis of mean-square error (MSE) estimation using a direct relationship between optimum estimation and certain partition functions. The paper consists of essentially two parts. In the first part, using the aforementioned relationship, we derive single-letter expressions of the mismatched MSE of a codeword (from a randomly selected code), corrupted by a Gaussian vector channel. In the second part, we provide several examples to demonstrate phase transitions in the behavior of the MSE. These examples enable us to understand more deeply and to gather intuition regarding the roles of the real and the mismatched probability measures in creating these phase transitions.
arXiv comment58 pages;Submitted to IEEE Trans. on Information Theory
References in corpus (4)
- Statistical Physics of Signal Estimation in Gaussian Noise: Theory and Examples of Phase Transitions
- Optimum estimation via gradients of partition functions and information measures: a statistical-mechanical perspective
- Statistical mechanics of typical set decoding
- Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons