跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2606.30064 · v2

Annealed Gibbs Measures with Data-Driven Interaction Potentials on Hierarchical Structures

首次提交 2026-06-29 17:57
版本更新 2026-11-17 09:06
雷达观测 2026-11-18 19:43
arXiv ↗PDF ↗

摘要

We construct annealed Gibbs measures on continuous interaction parameters and binary spins on Cayley trees of order k≥1k\geq 1, with coupling functions determined by an empirical loss. The interaction parameters and spins are distinct random variables: the former determine edge couplings, while the latter represent binary labels. The training data specify the coupling function and the joint Gibbs specification, rather than automatically selecting a unique Gibbs measure on interaction parameters. We derive necessary and sufficient compatibility conditions for the finite-volume joint densities. These conditions take the form of nonlinear integral equations for boundary laws and characterize the splitting annealed Gibbs measures constructed here. For k=1k=1, the translation-invariant equations reduce to positive compact integral operators. Under the stated hypotheses, they have a unique normalized positive solution. For k=2k=2, an explicit empirical-loss kernel reduces the translation-invariant equations to polynomial equations. In this case, we show that hierarchical learning systems may exhibit phase-transition phenomena: for certain empirical kernels on Cayley trees order two, multiple Gibbs measures on spins emerge beyond a critical inverse temperature, corresponding to distinct equilibrium prediction regimes. For a selected annealed Gibbs measure, we distinguish its marginal on interaction parameters from its conditional Gibbs measures on spins at fixed interaction parameters. Our results provide a new perspective on energy-based learning, where data do not merely determine an optimal model through minimization but define an entire probabilistic landscape of possible inference states.

作者备注:31 pages, 5 figures

期刊信息:J. Stat. Mech. (2026) 113204

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-17 09:06 · 最新观测版本

Annealed Gibbs Measures with Data-Driven Interaction Potentials on Hierarchical Structures

We construct annealed Gibbs measures on continuous interaction parameters and binary spins on Cayley trees of order k≥1k\geq 1, with coupling functions determined by an empirical loss. The interaction parameters and spins are distinct random variables: the former determine edge couplings, while the latter represent binary labels. The training data specify the coupling function and the joint Gibbs specification, rather than automatically selecting a unique Gibbs measure on interaction parameters. We derive necessary and sufficient compatibility conditions for the finite-volume joint densities. These conditions take the form of nonlinear integral equations for boundary laws and characterize the splitting annealed Gibbs measures constructed here. For k=1k=1, the translation-invariant equations reduce to positive compact integral operators. Under the stated hypotheses, they have a unique normalized positive solution. For k=2k=2, an explicit empirical-loss kernel reduces the translation-invariant equations to polynomial equations. In this case, we show that hierarchical learning systems may exhibit phase-transition phenomena: for certain empirical kernels on Cayley trees order two, multiple Gibbs measures on spins emerge beyond a critical inverse temperature, corresponding to distinct equilibrium prediction regimes. For a selected annealed Gibbs measure, we distinguish its marginal on interaction parameters from its conditional Gibbs measures on spins at fixed interaction parameters. Our results provide a new perspective on energy-based learning, where data do not merely determine an optimal model through minimization but define an entire probabilistic landscape of possible inference states.

查看此版本解读 →查看此版本原文 ↗