Sample complexity bounds for categorical Markov random fields via Discrete Diffusions
math.ST, cs.LG, stat.ML, stat.TH
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- Generative Modeling with Denoising Auto-Encoders and Langevin Sampling
- Optimal Inference Schedules for Masked Diffusion Models
- Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization
- Non-Asymptotic Convergence of Discrete Diffusion Models: Masked and Random Walk dynamics
- No-Regret Generative Modeling via Parabolic Monge-Amp\`ere PDE
- Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
- Vocabulary-size-independent Convergence of Discrete Diffusion Models: adjoint equations induce the right space
- Mercury: Ultra-Fast Language Models Based on Diffusion
- Flow Matching is Adaptive to Manifold Structures
- Nonparametric estimation of a factorizable density using diffusion models
- Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
- Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity
- From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
- Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
- Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
- Sharp Convergence Rates for Masked Diffusion Models
- Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
Related papers
- Conformal Prediction for Dyadic Regression Under Complex Missingness
- Bentkus-type asymptotic e-values
- High-Dimensional Asymptotics of Differentially Private PCA
- KL Convergence Guarantees for Score diffusion models under minimal data assumptions
- Geometric bias in eigenspace perturbation under random heterogeneous noise
- On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models