Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions
Abstract
Comparing two high-dimensional discrete distributions has always been a challenging task due to the exponentially growing state space and complex changes in interactions. A recent work suggests comparing distributions through a vector field trained using flow matching between two continuous distributions. The resulting vector field at mid-point vanishes if and only if two distributions identical. However, such a flow-based criterion does not naturally apply to discrete distributions. We extend this principle to the discrete domain and introduce the \emph{Zero Flux} criterion, a discrepancy based on local probability fluxes. Under independent coupling, we show that all local probability fluxes vanish at the midpoint if and only if two distributions are the same. This discrepancy decomposes the joint distributional difference into smaller, local contributions and can be efficiently estimated from samples. We establish finite sample error bounds for our estimator. Experiments on synthetic and real categorical data demonstrate reliable recovery of sparse dependence signals and stable tracking of distribution shifts in high dimensions.
Related
- Fully Discrete Active Flux Methods for the Euler Equations: Exploring Different Reconstructions and New Multi-Dimensional Evolution Operators
- Semi-discrete Active Flux method for two-dimensional hyperbolic systems with Coriolis source terms
- Combining Multiple Incomplete Astronomical Surveys to Estimate Galaxy Flux Distributions
- Weighted universal Value-at-Risk Superadditivity for discrete distributions
- Tensor network representations of discrete maximum entropy distributions via mean polytopes
BibTeX
@misc{wang2026zero,
title = {{Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions}},
author = {Leyang Wang and Yakun Wang and Song Liu and Taiji Suzuki},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.01472},
eprint = {2610.01472},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.01472},
}
RIS
TY - UNPB
TI - Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions
AU - Leyang Wang
AU - Yakun Wang
AU - Song Liu
AU - Taiji Suzuki
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.01472
UR - https://arxiv.org/abs/2610.01472
AB - Comparing two high-dimensional discrete distributions has always been a challenging task due to the exponentially growing state space and complex changes in interactions. A recent work suggests comparing distributions through a vector field trained using flow matching between two continuous distributions. The resulting vector field at mid-point vanishes if and only if two distributions identical. However, such a flow-based criterion does not naturally apply to discrete distributions. We extend this principle to the discrete domain and introduce the \emph{Zero Flux} criterion, a discrepancy based on local probability fluxes. Under independent coupling, we show that all local probability fluxes vanish at the midpoint if and only if two distributions are the same. This discrepancy decomposes the joint distributional difference into smaller, local contributions and can be efficiently estimated from samples. We establish finite sample error bounds for our estimator. Experiments on synthetic and real categorical data demonstrate reliable recovery of sparse dependence signals and stable tracking of distribution shifts in high dimensions.
ER -