A sharp convergence theory for the probability flow odes of diffusion models
Diffusion models, which convert noise into new data instances by learning to reverse a
diffusion process, have become a cornerstone in contemporary generative modeling. In this …
diffusion process, have become a cornerstone in contemporary generative modeling. In this …
Improved convergence rate for diffusion probabilistic models
G Li, Y Jiao - arXiv preprint arXiv:2410.13738, 2024 - arxiv.org
Score-based diffusion models have achieved remarkable empirical performance in the field
of machine learning and artificial intelligence for their ability to generate high-quality new …
of machine learning and artificial intelligence for their ability to generate high-quality new …
Convergence of score-based discrete diffusion models: A discrete-time analysis
Diffusion models have achieved great success in generating high-dimensional samples
across various applications. While the theoretical guarantees for continuous-state diffusion …
across various applications. While the theoretical guarantees for continuous-state diffusion …
Provable acceleration for diffusion models under minimal assumptions
While score-based diffusion models have achieved exceptional sampling quality, their
sampling speeds are often limited by the high computational burden of score function …
sampling speeds are often limited by the high computational burden of score function …
How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework
Discrete diffusion models have gained increasing attention for their ability to model complex
distributions with tractable sampling and inference. However, the error analysis for discrete …
distributions with tractable sampling and inference. However, the error analysis for discrete …