Paperlane

no. 16 · Tuesday 17 November 2026

Adaptive Reparametrized Time for Score-Based Diffusion Sampling

Yilie Huang, Wenpin Tang and Xun Yu Zhou

math.OC · v5 · 40 pp

Abstract

We study timestep allocation for score-based diffusion sampling, where the learned reverse-time dynamics is discretized on a finite grid. Uniform and hand-crafted schedules are standard, but their fixed, ad hoc prescriptions can be suboptimal. We propose Adaptive Reparameterized Time (ART), a continuous-time control formulation that learns a time change by treating sampling-clock speed as the control, so a uniform grid on the learned clock induces adaptive timesteps in diffusion time and a leading-order Euler error surrogate defines the allocation objective. To solve the resulting high-dimensional deterministic control problem, we introduce ART-RL, an auxiliary randomized Gaussian-policy formulation that turns schedule learning into continuous-time reinforcement learning. We prove ART-RL is equivalent to ART at optimality: the mean of the optimal Gaussian policy solves ART. We further establish policy evaluation and policy improvement characterizations and derive trajectory-based moment identities that yield implementable actor-critic updates. Experiments ranging from controlled low-dimensional settings to image generation show that ART-learned schedules, when plugged into existing samplers by changing only the timestep grid, consistently improve sample quality over strong baselines at matched budgets. The learned schedules also exhibit broad generalizability, transferring without retraining across sampling budgets, data sets, solvers, pipelines, and representation spaces.

comments
40 pages. Accepted for publication in the Journal of Machine Learning Research (JMLR). Updated to the final accepted manuscript
fields
Optimization and Control
pdf ↗ page arXiv:2607.02137 ↗