跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2605.10668 · v2

A Spectral Framework for Closed-Form Relative Density Estimation

首次提交 2026-05-11 22:51
版本更新 2026-11-16 21:35
雷达观测 2026-11-17 17:11
arXiv ↗PDF ↗

摘要

We propose a closed-form spectral framework for relative log-density estimation in linearly parameterized probabilistic models, including unnormalized and conditional models. This is achieved by representing the Kullback-Leibler (KL) divergence as an integral of weighted chi-squared divergences, converting KL estimation into a family of least-squares problems. We derive an explicit spectral formula based only on first- and second-order feature moments, yielding closed-form estimators of both divergences and log-density potentials for fixed features. The framework extends to a broad class of ff-divergences and can be combined with kernelization or feature learning with neural networks (with then only a closed form for the last layer). We prove convergence guarantees for the resulting estimators and empirically compare them on synthetic data with optimization-based variational formulations, including logistic and softmax regression for normalized conditional models.

作者备注:Published at Advances in Neural Processing Systems

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 · 2026-11-16 21:35 · 最新观测版本

A Spectral Framework for Closed-Form Relative Density Estimation

We propose a closed-form spectral framework for relative log-density estimation in linearly parameterized probabilistic models, including unnormalized and conditional models. This is achieved by representing the Kullback-Leibler (KL) divergence as an integral of weighted chi-squared divergences, converting KL estimation into a family of least-squares problems. We derive an explicit spectral formula based only on first- and second-order feature moments, yielding closed-form estimators of both divergences and log-density potentials for fixed features. The framework extends to a broad class of ff-divergences and can be combined with kernelization or feature learning with neural networks (with then only a closed form for the last layer). We prove convergence guarantees for the resulting estimators and empirically compare them on synthetic data with optimization-based variational formulations, including logistic and softmax regression for normalized conditional models.

查看此版本解读 →查看此版本原文 ↗