Matched Queries for Curvature and Density at Branching Junctions
Abstract
At a junction, a score field can reveal weighted tangent rays, yet these first-order quantities do not determine how individual branches bend or how their densities change away from the center. Recovering this missing information is necessary for describing local continuation beyond a single point, but finite observations must separate branchwise second-order effects while allowing error in the estimated center. We address this inverse problem using matched score queries at noise scales σ and λσ. For a finite union of C2,α half-branches in ℝD, the normalized score has the expansion Fσ=F0+σG+O(σ1+α). Matched subtraction cancels the tangent contribution and exposes G, which depends linearly on branchwise curvature and log-density slope. Given tangent directions and weights on distinct rays, G uniquely identifies all sD branch parameters, and sD scalar component observations are necessary. An O(σ2) center error introduces D translation modes, leading to (s+1)D observations under full-rank calibration, except for a translation-invariant full line. We also establish a perturbation bound and a conditional kernel-density-estimation rate. Experiments reproduce the predicted population and N−1/5 trends and remain full rank up to D=20 with 16 supplied branches. In end-to-end tests for D=3--$5$, a known-count first-order frontend yields full rank in all 135 population systems and a median relative jet error of 0.132. With strong first-order error, matched responses reduce median parameter error by a factor of 49.4 relative to naive tangent subtraction.
Related
- Left tail asymptotics for the density of supercritical branching processes in random environment
- Extremal Lin--Lu--Yau Curvature: Graph Density, Girth, and Short Cycles
- On the Sample Complexity of Active Learning with Membership Queries
- Accelerated Algorithms for Stochastic Monotone Inclusions with Fixed Queries
- Hypothesis Testing with Conditional Queries: Learnability and the Value of Interaction
BibTeX
@misc{zhao2026matched,
title = {{Matched Queries for Curvature and Density at Branching Junctions}},
author = {Ziqi Zhao and Qingjian Ni},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.01319},
eprint = {2609.01319},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.01319},
}
RIS
TY - UNPB
TI - Matched Queries for Curvature and Density at Branching Junctions
AU - Ziqi Zhao
AU - Qingjian Ni
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.01319
UR - https://arxiv.org/abs/2609.01319
AB - At a junction, a score field can reveal weighted tangent rays, yet these first-order quantities do not determine how individual branches bend or how their densities change away from the center. Recovering this missing information is necessary for describing local continuation beyond a single point, but finite observations must separate branchwise second-order effects while allowing error in the estimated center. We address this inverse problem using matched score queries at noise scales σ and λσ. For a finite union of C^2,α half-branches in ℝ^D, the normalized score has the expansion F_σ=F_0+σG+O(σ^1+α). Matched subtraction cancels the tangent contribution and exposes G, which depends linearly on branchwise curvature and log-density slope. Given tangent directions and weights on distinct rays, G uniquely identifies all sD branch parameters, and sD scalar component observations are necessary. An O(σ^2) center error introduces D translation modes, leading to (s+1)D observations under full-rank calibration, except for a translation-invariant full line. We also establish a perturbation bound and a conditional kernel-density-estimation rate. Experiments reproduce the predicted population and N^−1/5 trends and remain full rank up to D=20 with 16 supplied branches. In end-to-end tests for D=3--$5$, a known-count first-order frontend yields full rank in all 135 population systems and a median relative jet error of 0.132. With strong first-order error, matched responses reduce median parameter error by a factor of 49.4 relative to naive tangent subtraction.
ER -