SOURCE-LINKED INTELLIGENCE

The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

We study a class of product-reference diffusion algorithms for sampling from a discrete distribution. We show that their sampling performance can be characterized using a path-based measure of data geometry that we call the interaction growth complexity (IGC). We show that a bivariate IGC kernel gives an exact representation of both the KL discretization error and a simple one-step upper bound. The simpler univariate IGC density can be used to study the effect of stepsize choices on the iteration complexity required to obtain $ε$-accurate samples in KL divergence. Samplers that traverse the pa

Read original source ↗ Open in workspace

recordType

paper

region

Global