Saved in:
Bibliographic Details
Main Authors: Tavakoli, Hassan, Nguyen, Thinh, Bose, Bella
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.11352
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913115454570496
author Tavakoli, Hassan
Nguyen, Thinh
Bose, Bella
author_facet Tavakoli, Hassan
Nguyen, Thinh
Bose, Bella
contents We study the problem of estimating a parametric discrete memoryless channel \( p(y \mid x; \boldsymbolθ) \) when the transmitter selects its input distribution \( π\) to maximize mutual information under the true parameter \( \boldsymbolθ^* \). Using only i.i.d.\ observations of the channel output, we aim to jointly estimate the capacity-achieving input distribution \( \boldsymbolπ^* \) and the true channel parameter \( \boldsymbolθ^* \). In general, recovery of \( \boldsymbolπ^* \) and \( \boldsymbolθ^* \) can be challenging. To that end, we propose two efficient algorithms based on the Blahut--Arimoto (BA) optimality conditions: (i) a bilevel fixed-point method and (ii) an augmented Lagrangian method. Empirical results demonstrate that both proposed algorithms successfully recover the true \( \boldsymbolθ^* \) and \( \boldsymbolπ^* \), whereas a naive maximum-likelihood approach that ignores the mutual-information maximization constraint fails to do so.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11352
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Parameter Estimation of Mutual Information Maximized Channels
Tavakoli, Hassan
Nguyen, Thinh
Bose, Bella
Information Theory
Signal Processing
We study the problem of estimating a parametric discrete memoryless channel \( p(y \mid x; \boldsymbolθ) \) when the transmitter selects its input distribution \( π\) to maximize mutual information under the true parameter \( \boldsymbolθ^* \). Using only i.i.d.\ observations of the channel output, we aim to jointly estimate the capacity-achieving input distribution \( \boldsymbolπ^* \) and the true channel parameter \( \boldsymbolθ^* \). In general, recovery of \( \boldsymbolπ^* \) and \( \boldsymbolθ^* \) can be challenging. To that end, we propose two efficient algorithms based on the Blahut--Arimoto (BA) optimality conditions: (i) a bilevel fixed-point method and (ii) an augmented Lagrangian method. Empirical results demonstrate that both proposed algorithms successfully recover the true \( \boldsymbolθ^* \) and \( \boldsymbolπ^* \), whereas a naive maximum-likelihood approach that ignores the mutual-information maximization constraint fails to do so.
title Parameter Estimation of Mutual Information Maximized Channels
topic Information Theory
Signal Processing
url https://arxiv.org/abs/2605.11352