arXiv Machine Learning
Discrete Diffusion Models are Minimax Optimal Under Sparsity
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 24
Minimax Optimality of Score-Entropy Discrete Diffusion
arXiv:2608.20635v1 Announce Type: cross Abstract: Discrete diffusion models have demonstrated strong performance across a range of datasets, including natural language data and graph-structured data....
arXiv Machine Learning
Oct 5
Jumping up and down: Denoiser diffusion models for discrete ordinal data
arXiv:2610.02754v1 Announce Type: new Abstract: Diffusion models are highly developed in continuous spaces for image and video domains. Recently, major advances have been made for discrete diffusion...
arXiv Machine Learning
Aug 6
Regularization can make diffusion models more efficient
arXiv:2502. 09151v3 Announce Type: replace Abstract: Diffusion models are one of the key architectures of generative AI.
arXiv AI
Jun 10
Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech
arXiv:2606. 09962v1 Announce Type: cross Abstract: Continuous diffusion for categorical data is a framework belonging to the diffusion family and aiming at generating discrete data.
arXiv Machine Learning
Aug 10
Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
arXiv:2409. 18804v3 Announce Type: replace-cross Abstract: Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond.
arXiv Machine Learning
Oct 16
Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion
The paper presents a theoretical analysis of score mismatch in discrete diffusion models, deriving a KL divergence upper bound that quantifies the bias introduced when the training and target distributions differ. It examines partial-observation constraints such as text infilling and sentence completion, showing that the Conditional SEDD sampler can incur a bias that grows with dimension, vocabulary size, and compatibility. To mitigate this, the authors propose a Randomized Hard Clamping (RHC) sampler for coordinatewise set constraints, demonstrating through experiments that it effectively reduces bias and improves sampling performance.