An information identity reveals the geometry of deviation events
Abstract
In a deviation event, the empirical measure of n independent draws lands in a set of distributions. The exponent of its probability splits, at every n, into two nonnegative terms. The first is the rate: n times the relative entropy, from the population, of the distribution of a typical draw under the event. The second is the dependence that conditioning induces among the draws, measured by their total correlation. Their relative sizes depend on the geometry of the set. This paper focuses on this exact split and on the geometry that the interplay of its two terms reveals. The dependence vanishes exactly when the event confines every draw to a single set, and the classical rate of that constraint is exact. On a set invariant under a compact group that fixes the population and leaves no invariant set of intermediate probability, the rate vanishes; uniform convergence over a hypothesis class that such a group permutes is one. On a half-space whose threshold sits a fixed number of standard errors above the mean, the fraction of the exponent that is dependence tends to a function of the event's probability alone. On a set split into pieces, the dependence is the pieces' average plus n times the Jensen-Shannon divergence of their marginals, minus the entropy of their weights. The split extends to a general reference law. When the information projection is such a law, the split gives the exact value of the expectation in the exponential change of measure to the projection.
Related
- Deviation probabilities for global events in two dimensions (I): independent excursions
- Finite Weil Jets, Identity Transfer, and the Exponential Geometry of Proper Orthogonal Tensors
- Geometry-informed importance sampling for rare events
- Scattering Measures and Information Geometry
- When Geometry Shapes Information in Pursuit-Evasion Games
BibTeX
@misc{balsubramani2026information,
title = {{An information identity reveals the geometry of deviation events}},
author = {Akshay Balsubramani},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38159},
eprint = {2609.38159},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38159},
}
RIS
TY - UNPB
TI - An information identity reveals the geometry of deviation events
AU - Akshay Balsubramani
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38159
UR - https://arxiv.org/abs/2609.38159
AB - In a deviation event, the empirical measure of n independent draws lands in a set of distributions. The exponent of its probability splits, at every n, into two nonnegative terms. The first is the rate: n times the relative entropy, from the population, of the distribution of a typical draw under the event. The second is the dependence that conditioning induces among the draws, measured by their total correlation. Their relative sizes depend on the geometry of the set. This paper focuses on this exact split and on the geometry that the interplay of its two terms reveals. The dependence vanishes exactly when the event confines every draw to a single set, and the classical rate of that constraint is exact. On a set invariant under a compact group that fixes the population and leaves no invariant set of intermediate probability, the rate vanishes; uniform convergence over a hypothesis class that such a group permutes is one. On a half-space whose threshold sits a fixed number of standard errors above the mean, the fraction of the exponent that is dependence tends to a function of the event's probability alone. On a set split into pieces, the dependence is the pieces' average plus n times the Jensen-Shannon divergence of their marginals, minus the entropy of their weights. The split extends to a general reference law. When the information projection is such a law, the split gives the exact value of the expectation in the exponential change of measure to the projection.
ER -