跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24213 · v1

Continuous Noisy-Loop Models

首次提交 2026-11-18 18:52
版本更新 2026-11-18 18:52
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Efficient learning and inference need not imply a compact probabilistic circuit. We quantify this distinction for continuous noisy readings of agreement between adjacent latent spins on a known square grid with dd edges. With known margins and bounded Lipschitz channels, minimax squared Hellinger risk is Θ(min⁡{1,dN−2/3})Θ(\min\{1,dN^{-2/3}\}) from NN independent vectors, without a reliability lower bound. A spline estimator reaches this rate in polynomial arithmetic time given a fixed positive reliability bound; an exponential-size mixture removes that requirement. At fixed positive reliability, nonnegative decomposable circuits need exp⁡(Θ(d))\exp(Θ(\sqrt d)) nodes for fixed total-variation error below one, even when each leaf uses at most αdαd coordinates, 0<α<10<α<1. Optimal Kullback--Leibler (KL) approximation error is Θ(d/max⁡{log⁡d,ℓ})Θ(d/\max\{\log d,\sqrt\ell\}) in either direction with at most drd^r nodes and leaf scopes ℓ≤αd\ell\leqαd, for fixed r>1r>1 and 0<α<2/30<α<2/3. Node counts exclude leaf computation. For three fixed masks, optimal joint conditional KL has order d/log⁡dd/\log d when ℓ≤(log⁡d)2\ell\leq(\log d)^2. Local cycle identities relate joint divergence to identifiable channel products and separate weak-channel recovery from density estimation. Factorized evidence preserves a planar zero-field Ising model: given local integrals, exact queries cost O(d3/2)O(d^{3/2}) arithmetic operations and one root extraction.

作者备注:51 pages, 7 figures

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

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

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。

v1 · 2026-11-18 18:52 · 最新观测版本

Continuous Noisy-Loop Models

Efficient learning and inference need not imply a compact probabilistic circuit. We quantify this distinction for continuous noisy readings of agreement between adjacent latent spins on a known square grid with dd edges. With known margins and bounded Lipschitz channels, minimax squared Hellinger risk is Θ(min⁡{1,dN−2/3})Θ(\min\{1,dN^{-2/3}\}) from NN independent vectors, without a reliability lower bound. A spline estimator reaches this rate in polynomial arithmetic time given a fixed positive reliability bound; an exponential-size mixture removes that requirement. At fixed positive reliability, nonnegative decomposable circuits need exp⁡(Θ(d))\exp(Θ(\sqrt d)) nodes for fixed total-variation error below one, even when each leaf uses at most αdαd coordinates, 0<α<10<α<1. Optimal Kullback--Leibler (KL) approximation error is Θ(d/max⁡{log⁡d,ℓ})Θ(d/\max\{\log d,\sqrt\ell\}) in either direction with at most drd^r nodes and leaf scopes ℓ≤αd\ell\leqαd, for fixed r>1r>1 and 0<α<2/30<α<2/3. Node counts exclude leaf computation. For three fixed masks, optimal joint conditional KL has order d/log⁡dd/\log d when ℓ≤(log⁡d)2\ell\leq(\log d)^2. Local cycle identities relate joint divergence to identifiable channel products and separate weak-channel recovery from density estimation. Factorized evidence preserves a planar zero-field Ising model: given local integrals, exact queries cost O(d3/2)O(d^{3/2}) arithmetic operations and one root extraction.

查看此版本解读 →查看此版本原文 ↗