Paperlane

no. 16 · Tuesday 17 November 2026

A Spectral Framework for Closed-Form Relative Density Estimation

Francis Bach

math.OC · v2

Abstract

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 $f$-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.

comments
Published at Advances in Neural Processing Systems
fields
Optimization and Control, Statistics Theory
pdf ↗ page arXiv:2605.10668 ↗