Uniform Discrete Diffusion Models are Minimax Optimal for Estimating Distributions with Small Effective Support Size

arXiv:2610.07655 · stat.ML, cs.LG · Submitted 2026-10-06 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-10-06

Updated: 2026-10-06

Terminology

• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes

Sources

• TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
• Nearly Minimax Discrete Distribution Estimation in Kullback-Leibler Divergence with High Probability
• Instance-Optimality for Private KL Distribution Estimation

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier