SOURCE-LINKED INTELLIGENCE

Schedule optimization for tau-leaping in masked discrete diffusion

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Masked discrete diffusion models are commonly accelerated using the so-called tau-leaping discretization method, which reveals several coordinates in parallel at each sampling step. The sampler replaces the joint conditional law of each revealed block by a product distribution, incurring a factorization error $\varepsilon_\text{fact}$ present even with perfectly learned predictors. We analyze the standard sampler on $N$ coordinates with $K$ sampling steps, whose random block sizes depend on a denoising schedule. Our analysis uses an exact integral representation of $\varepsilon_\text{fact}$ in

Read original source ↗ Open in workspace

recordType

paper

region

Global