A Poisson Transition and Bias Law for KSG Mutual-Information Estimation
cs.IT, math.IT
Submitted: 2026-10-27
Updated: 2026-10-27
License: http://creativecommons.org/licenses/by/4.0/
The gist: We quantify the error of the strict-radius Kraskov--Stögbauer--Grassberger (KSG-1) mutual-information estimator on a Gaussian channel as the sample size n grows and the channel becomes nearly…
Abstract
We quantify the error of the strict-radius Kraskov--Stögbauer--Grassberger (KSG-1) mutual-information estimator on a Gaussian channel as the sample size n grows and the channel becomes nearly deterministic. For fixed dimension p and neighbor index k, we define the resolution parameter u n=ne-I n, where I n is the true mutual information in nats. When u n to u in(0, infinity), we prove that the estimation error converges in mean square to a computable deterministic bias B p,k(u). Sampling fluctuations therefore vanish, while an additive bias can persist. We derive this bias from an explicit marked-Poisson law for the neighborhood counts, characterize its small- u asymptotics, and show that it tends to zero as u to infinity. The same law describes how often neighborhoods saturate, meaning that they make the largest possible contribution to the estimate. The limiting saturation probability decreases continuously and strictly from one to zero, allowing a Gaussian-model bias correction on fixed critical intervals. Finite-sample experiments show substantial bias even when the true information lies below the estimator's logarithmic ceiling and saturated neighborhoods are rare. Saturation-based correction reduces estimation error in these experiments, though recovering the resolution parameter from the observed saturation fraction can remain difficult when saturation is rare.
Related papers
- The Gaussian Multiuser Channel Capacity Region
- The mathematical landscape of partial information decomposition: A comprehensive review of properties and measures
- Electromagnetic Signal and Information Theory: A Continuous-Aperture Array Perspective
- Analytically Characterized Optimal Power Control for Signal-Level-Integrated Sensing, Computing and Communication in Federated Learning
- Information Spectrum Methods for Multiple-Access Channels--Part I: epsilon-Capacity Regions in the Mixed Gaussian Case
- Seed Recycling: Explicit Codes for Mixed Synchronization Errors Matching the Leading Term of the Gilbert--Varshamov Bound