Score-based diffusion models have emerged as powerful tools in generative modeling, yet their theoretical foundations remain underexplored. In this work, we focus on the Wasserstein convergence analysis of score-based diffusion models. Specifically, we investigate the impact of various discretization schemes, including Euler discretization, exponential integrators, and midpoint randomization methods. Our analysis provides a quantitative comparison of these discrete approximations, emphasizing their influence on convergence behavior. Furthermore, we explore scenarios where Hessian information is available and propose an accelerated sampler based on the local linearization method. We demonstrate that this Hessian-based approach achieves faster convergence rates of order $\widetilde{\mathcal{O}}\left(\frac{1}{\varepsilon}\right)$ significantly improving upon the standard rate $\widetilde{\mathcal{O}}\left(\frac{1}{\varepsilon^2}\right)$ of vanilla diffusion models, where $\varepsilon$ denotes the target accuracy.
Skolkovo Institute of Science and Technology(斯科尔科沃科学技术学院);Moscow Institute of Physics and Technology(莫斯科物理技术学院);Massachusetts Institute of Technology(麻省理工学院);Artificial Intelligence Research Institute(人工智能研究所)
Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization
Graduate School of Information Science and Technology, Hokkaido University, Japan(信息科学与技术研究生学校,北海道大学,日本);Bioinformatics Center, Kyoto University, Japan(生物信息学中心,京都大学,日本);Institute of Information Technology, Vietnam Academy of Science and Technology, Vietnam(信息技术研究所,越南科学与技术学院,越南)
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California, San Diego(加州大学圣地亚哥分校);National University of Singapore(新加坡国立大学);University of California, Los Angeles(加州大学洛杉矶分校);Sri Aurobindo International Centre of Education(斯里阿罗bindo国际教育中心)
Transport-Coupled Bayesian Flows for Molecular Graph Generation
School of Computer Science, Wuhan University(武汉大学计算机学院);Department of Computing, Macquarie University(麦考瑞大学计算系);Wuhan University Shenzhen Research Institute(武汉大学深圳研究院)
Wasserstein Convergence of Critically Damped Langevin Diffusions
Sorbonne Université and Université Paris Cité, CNRS, LPSM(索邦大学和巴黎西岱大学,法国国家科学研究中心,LPSM);LOPF, Califrais’ Machine Learning Lab(LOPF,Califrais机器学习实验室);LMO, Université Paris-Saclay, UMR CNRS 8628, Institut Universitaire de France(LMO,巴黎萨克雷大学,CNRS联合研究单位8628,法国高等研究院);CREST, Groupe ENSAE-ENSAI, ENSAE Paris, Institut Polytechnique de Paris(CREST,ENSAE-ENSAI集团,巴黎ENSAE,巴黎理工学院)
Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data
Department of Statistics, University of Michigan(密歇根大学统计学系);Google DeepMind(谷歌DeepMind);Department of Statistics, University of California, Berkeley(加州大学伯克利分校统计学系);Department of Electrical Engineering and Computer Sciences, UC Berkeley(加州大学伯克利分校电气工程与计算机科学系)