Conditional Fisher-Information Central Limit Theorems under Log-Concavity with Information-Theoretic Consequences
Abstract
We establish conditional central limit theorems in Fisher information under log-concavity in every fixed dimension. For conditionally centered normalized sums, after whitening by the averaged conditional covariance, the averaged conditional Fisher information converges to the dimension if and only if it is finite at one convolution level. The scalar criterion follows as the one-dimensional case; we also provide an independent scalar proof based on a second-order continuity theorem for Fisher production on Gaussian-smoothed, tail-controlled classes. For the original sums, the averaged Fisher information matrix converges in operator norm to the inverse averaged conditional covariance. Consequently, the conditional relative Fisher information with respect to the limiting Gaussian law vanishes, and the Gaussian logarithmic Sobolev inequality yields convergence in conditional relative entropy and conditional entropy. We give two operational consequences. For any fixed finite-constellation low-power input, the first-order conditional mutual-information slope converges to the Gaussian-noise benchmark. For Gaussian signaling at any fixed signal covariance, the mutual-information gap from that benchmark is bounded by the conditional relative Fisher deficit and hence vanishes asymptotically.
Related
- Measuring Learned Equivariance: An Information Theoretic Approach
- A Sample-Based Approach for Hierarchical Information-Theoretic Compression of Probabilistic Occupancy Grids
- Learning Rules, Memorizing Facts: An Information-Theoretic View of Hallucination
- Efficient Robust Learning at the Information-Theoretic Limit
- The Pauli Lightcone: Information-Theoretic Error Mitigation Beyond the Autocorrelation
BibTeX
@misc{ye2026conditional,
title = {{Conditional Fisher-Information Central Limit Theorems under Log-Concavity with Information-Theoretic Consequences}},
author = {Tong Ye and Liu-Quan Yao},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.07150},
eprint = {2609.07150},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.07150},
}
RIS
TY - UNPB
TI - Conditional Fisher-Information Central Limit Theorems under Log-Concavity with Information-Theoretic Consequences
AU - Tong Ye
AU - Liu-Quan Yao
PY - 2026
DA - 2026/09/07
PB - arXiv
DO - 10.48550/arxiv.2609.07150
UR - https://arxiv.org/abs/2609.07150
AB - We establish conditional central limit theorems in Fisher information under log-concavity in every fixed dimension. For conditionally centered normalized sums, after whitening by the averaged conditional covariance, the averaged conditional Fisher information converges to the dimension if and only if it is finite at one convolution level. The scalar criterion follows as the one-dimensional case; we also provide an independent scalar proof based on a second-order continuity theorem for Fisher production on Gaussian-smoothed, tail-controlled classes. For the original sums, the averaged Fisher information matrix converges in operator norm to the inverse averaged conditional covariance. Consequently, the conditional relative Fisher information with respect to the limiting Gaussian law vanishes, and the Gaussian logarithmic Sobolev inequality yields convergence in conditional relative entropy and conditional entropy. We give two operational consequences. For any fixed finite-constellation low-power input, the first-order conditional mutual-information slope converges to the Gaussian-noise benchmark. For Gaussian signaling at any fixed signal covariance, the mutual-information gap from that benchmark is bounded by the conditional relative Fisher deficit and hence vanishes asymptotically.
ER -