Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Model
Francis Bach
We study ridge-regularized log-density-ratio estimation in the Gaussian location model with a common covariance matrix. By affine invariance, the model is written as q N(0,…
cs.LG2026
A Spectral Framework for Closed-Form Relative Density Estimation
Francis Bach
We propose a closed-form spectral framework for relative log-density estimation in linearly parameterized probabilistic models, including unnormalized and conditional models. This…
cs.LG2026
Optimal Denoising in Score-Based Generative Models: The Role of Data Regularity
Eliot Beyler, Francis Bach
Score-based generative models achieve state-of-the-art sampling performance by denoising a distribution perturbed by Gaussian noise. In this paper, we focus on a single determinist…