Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions
Abstract
This note studies the geometry of full conformal prediction (FullCP) regions generated by an empirical energy-form pairwise score. Candidate-score convexity alone does not guarantee connected FullCP regions, even for empirical averages of losses convex in the candidate argument. For the energy-form score, each leave-one-out training comparison reduces exactly to a pairwise-dissimilarity sublevel condition. Under symmetry, a constant diagonal, a diagonal lower bound, and attainment of the associated Fréchet-type objective, all comparison regions share a minimizer; if they are convex, every nontrivial exact conformal region is star-shaped about that point. For power distances ρβ(x,y)=|x−y|β, this geometry holds for β≥1, while the conventional energy score is strictly proper for 0<β<2. For d=1,β=1, every nontrivial empirical-CRPS FullCP region is a nonempty closed interval (possibly ℝ when m=1). For 1<β<2 and m≥2, explicit data-checkable derivative bounds give Lipschitz control of the radial exits and exact conformal radial function. Combined with directional root search and classical Lipschitz extensions, they yield certified inner and outer radial envelopes of width at most δ+2L̃h𝒰 and same-ray Hausdorff guarantees. An analytic two-dimensional example shows why preserving star-shaped but nonconvex geometry can matter. A staged two-dimensional study finds modest but systematic tightening of the generic certificate and frequent robust nonconvexity witnesses, with detected normalized radial departures typically small. The method is intended for low-dimensional multivariate outputs rather than high-dimensional scaling or runtime improvement.
Related
- The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
- Certified Adaptive Refresh: Anytime-Valid Monitoring for Federated Conformal RAG
- Region bounds, error margins and certified positivity in the numerical conformal bootstrap; Or the first mathematically rigorous bounds on the 3d Ising CFT critical exponents
- Conformal prediction regions for dependent censored lifetimes
- CoCoNet: Convex Conformal Network for Multi-Dimensional Uncertainty Regions
BibTeX
@misc{feng2026commoncenter,
title = {{Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions}},
author = {Yiheng Feng},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.24964},
eprint = {2608.24964},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.24964},
}
RIS
TY - UNPB
TI - Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions
AU - Yiheng Feng
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2608.24964
UR - https://arxiv.org/abs/2608.24964
AB - This note studies the geometry of full conformal prediction (FullCP) regions generated by an empirical energy-form pairwise score. Candidate-score convexity alone does not guarantee connected FullCP regions, even for empirical averages of losses convex in the candidate argument. For the energy-form score, each leave-one-out training comparison reduces exactly to a pairwise-dissimilarity sublevel condition. Under symmetry, a constant diagonal, a diagonal lower bound, and attainment of the associated Fréchet-type objective, all comparison regions share a minimizer; if they are convex, every nontrivial exact conformal region is star-shaped about that point. For power distances ρ_β(x,y)=|x−y|^β, this geometry holds for β≥1, while the conventional energy score is strictly proper for 0<β<2. For d=1,β=1, every nontrivial empirical-CRPS FullCP region is a nonempty closed interval (possibly ℝ when m=1). For 1<β<2 and m≥2, explicit data-checkable derivative bounds give Lipschitz control of the radial exits and exact conformal radial function. Combined with directional root search and classical Lipschitz extensions, they yield certified inner and outer radial envelopes of width at most δ+2L̃h_𝒰 and same-ray Hausdorff guarantees. An analytic two-dimensional example shows why preserving star-shaped but nonconvex geometry can matter. A staged two-dimensional study finds modest but systematic tightening of the generic certificate and frequent robust nonconvexity witnesses, with detected normalized radial departures typically small. The method is intended for low-dimensional multivariate outputs rather than high-dimensional scaling or runtime improvement.
ER -