Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions

• URL: http://arxiv.org/abs/2608.24964v2
• Date: Tue, 01 Sep 2026 09:44:26 GMT
• Title: Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions
• Abstract summary: This note focuses on the geometry of conformal prediction (FullCP) regions generated by an empirical energy-form pairwise score.<n>For $12$ and $mge2$, explicit data-checkable derivative bounds give Lipschitz control of the radial exits and exact conformal radial function.
• Score: 5.188221150628459
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 $ρ_β(x,y)=\|x-y\|^β$, this geometry holds for $β\ge1$, 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 $\mathbb R$ when $m=1$). For $1<β<2$ and $m\ge2$, 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 $δ+2\widetilde Lh_{\mathcal U}$ 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.

Related papers

• Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality [0.0]
  Kolmogorov-Arnold Networks (KANs) replace fixed activations in deep architectures.<n>Family of edge activations derived from Banach duality maps.<n>Learnable exponents provide an interpretable, relative signal.
  arXiv  Detail & Related papers  (2026-08-26T13:53:13Z)
• Recovering Weighted Tangent Geometry from a Single-Scale Score Field [5.081899241065076]
  We show that a score field at one noise level determines a weighted tangent geometry when the branch center and homogeneity degree $d$ are unknown.<n>We also prove that for finite planar $C1,$ branches with positive $C0,$ densities, we prove $O()$ convergence from the finite-noise score to its tangent model.
  arXiv  Detail & Related papers  (2026-08-23T10:07:12Z)
• Sparse anisotropic positive maps for qutrit entanglement: exact indecomposability and PPT geometry [0.0]
  We introduce and analyze an exactly solvable family of sparse bistochastic positive maps on qutrits.<n>We show that positivity holds exactly on the square $0le w,zle2/3$, complete positivity on the smaller square $0le w,zle2/3$, and decomposability is lost precisely outside a quarter circle in the corner.<n>Although $W_*$ is not optimal, we give an explicit optimal refinement whose detection region on this family is strictly larger.
  arXiv  Detail & Related papers  (2026-07-14T07:55:02Z)
• Complex spacing ratio statistics in the partially open asymmetric quantum baker map [36.94429692322632]
  We study the complex eigenvalue statistics of the asymmetric quantum baker map with partial projective openings.<n>We find a smooth crossover from a quasi-1D spectral regime, where eigenvalues cluster near the unit circle and the phase distribution of $z$ is peaked.<n>Both the number of open channels $M$ and the reflectivity $$ modulate this crossover, and $$ provides an additional continuous control even at fixed opening size.
  arXiv  Detail & Related papers  (2026-07-08T19:24:35Z)
• Optimization Geometrodynamics: Variational Reduction and Interaction Curvature [0.0]
  We develop geometrodynamics as a variational theory of this hidden determinant pushforward.<n>For affine pre-reductions, the induced interaction curvature is the negative-semidefinite operator $-G*H-1G$.<n>We prove a global analytic bundle with closed totally geodesic fibers and a unique analytic nearest-controller section.
  arXiv  Detail & Related papers  (2026-07-07T18:42:00Z)
• Dimension Reduction for Curves: Simplified and Generalized [56.23281156053955]
  We revisit random projections for reducing the dimension of high-dimensional polygonal curves.<n>We give a simplified proof of the known $O(varepsilon-2log(nm))$ bound on the target dimension of a random projection.<n>Our proof is based on the concept of sparse oblivious subspace embeddings.
  arXiv  Detail & Related papers  (2026-07-03T08:48:35Z)
• Non-asymptotic Tail Bounds for the Kostlan--Shub--Smale Field: Tensor PCA and Spherical $k$-Spin Complexity [0.6627152091494143]
  This paper builds a hierarchy of explicit, non-asymptotic tail bounds for the supremum of the Kostlan--Shub--Smale random field on the sphere.<n>It applies it to two problems: Spiked PCA and the landscape of the spherical $k$-spin model.
  arXiv  Detail & Related papers  (2026-06-16T08:27:25Z)
• Optimal Dimension-Free Sampling for Regularized Classification [56.72526267755301]
  We prove optimal sampling bounds achieving $(1pmvarepsilon)$-relative error for a broad class of Lipschitz continuous classification loss functions.<n>This includes important functions such as logistic and sigmoid loss, hinge loss, and ReLU loss, as prominent and popular representative examples.
  arXiv  Detail & Related papers  (2026-05-22T15:05:33Z)
• Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds [61.14405512940818]
  We show that Score-based generative models are trained in high-dimensional ambient spaces.<n>We use a ReLU implementation of nearest-projection coordinates via finite intrinsic anchors and Gauss Newton.
  arXiv  Detail & Related papers  (2026-05-15T10:20:05Z)
• Provably Adaptive Linear Approximation for the Shapley Value and Beyond [73.0940890296463]
  A fundamental and long-standing challenge is their efficient approximation.<n>We develop a linear-space algorithm that requires $P(|hatboldsymbol-boldsymbol|_2geq)leq $ for all commonly used semi-values.<n>Our algorithm allows explicit minimization of the mean square error for each specific utility function.
  arXiv  Detail & Related papers  (2026-04-09T16:38:14Z)
• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• Calibrated Plane--Convex Microcavity for Room-Temperature Polaritons with Geometric \(g\)-Scaling [0.6553834611557042]
  We present a geometric plane--1/2 open microcavity that supports roomtemperature polariton and offers a simple handle on spectroscopy.<n>The platform establishes a compact, broadly compatible testbed for room-temperature polaritons.
  arXiv  Detail & Related papers  (2025-12-14T06:15:03Z)
• Witness wedges in fidelity-deviation plane: separating teleportation advantage and Bell-inequality violation [0.0]
  We develop a unified framework to analyze quantum teleportation through the joint geometry of two complementary figures of merit.<n>In particular, any measured pair $(F D)$ can be ported into a visibility estimate for isotropic resources.
  arXiv  Detail & Related papers  (2025-11-26T05:43:31Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.