Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis
arXiv:2610.12052v1 Announce Type: new Abstract: Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear. In this work, we leverage Gaussian distributions to isolate this phenomenon. We establish 2-Wasserstein convergence bound…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-09 04:00 · arXiv stat.ML
Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis