JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models
JAGG approximates intermediate-step Jacobians via $t$-weighted interpolation of the endpoint Jacobians, then aggregates per-step upstream signals into two composite gradients applied through a single joint backward pass, and it is proved this interpolation is exact when the velocity is linear in $(z,t)$, and a cosine-s...