Proves global GD convergence on reverse Fisher divergence for GMM score matching to single-Gaussian targets from arbitrary init and to separated GMM targets under random init.
Learning general Gaussian mixtures with efficient score matching.arXiv preprint arXiv:2404.18893
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Recasting diffusion noise schedule design as optimal control on Fisher information yields sufficient conditions for O(d/n) sampling error and parametric closed-form schedules that generalize exponential/sigmoid ones and improve empirical performance.
Diffusion-based denoising score matching avoids the mode-separation degradation that affects vanilla score matching error bounds, via suitable hyperparameter choice.
citing papers explorer
-
Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence
Proves global GD convergence on reverse Fisher divergence for GMM score matching to single-Gaussian targets from arbitrary init and to separated GMM targets under random init.
-
Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
Recasting diffusion noise schedule design as optimal control on Fisher information yields sufficient conditions for O(d/n) sampling error and parametric closed-form schedules that generalize exponential/sigmoid ones and improve empirical performance.
-
Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation
Diffusion-based denoising score matching avoids the mode-separation degradation that affects vanilla score matching error bounds, via suitable hyperparameter choice.