#data science
Jul 2026
Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
This analysis quantifies the role of the reweighting factor in the score approximation error, providing theoretical guidance for weighting choices used in practice, and develops a Neural Tangent Kernel analysis tailored to diffusion training with stochastic gradients.
Stanislas Strasman, Sobihan Surendran, S. Le Corff
· arXiv.org · 0 citations