We present a probabilistic model for natural images which is based on Gaussian scale mixtures and a simple multiscale representation. In contrast to the dominant approach to modeling whole images focusing on Markov random fields, we formulate our model in terms of a directed graphical model. We show that it is able to generate images with interesting higher-order correlations when trained on natural images or samples from an occlusion based model. More importantly, the directed model enables us to perform a principled evaluation. While it is easy to generate visually appealing images, we demonstrate that our model also yields the best performance reported to date when evaluated with respect to the cross-entropy rate, a measure tightly linked to the average log-likelihood.
Universality of Gaussian-Mixture Reverse Kernels in Conditional Diffusion
Center for Mathematics and Interdisciplinary Sciences, Fudan University(复旦大学数学与交叉科学中心);Shanghai Institute for Mathematics and Interdisciplinary Sciences (SIMIS)(上海数学与交叉科学研究院(SIMIS));Northeastern University(东北大学);Infectious Diseases Division, icddr,b(icddr,b传染病部门);Rutgers University(罗格斯大学)
Overcoming critical slowing down in frustrated spin systems by learned multiscale sampling
SISSA — International School for Advanced Studies and INFN(国际高等研究学院和意大利国家核物理研究所);Laboratoire de Physique Statistique, École normale supérieure, PSL Research University(巴黎高等师范学院统计物理实验室,PSL研究大学);Department of Physics, Duke University(杜克大学物理系);Department of Chemistry, Duke University(杜克大学化学系)
Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models
School of Management, University of Science and Technology of China(中国科学技术大学管理学院);Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院)
Gradient-free variational learning with conditional mixture networks
VERSES AI Research Lab(VERSES AI研究实验室);Max Planck Institute of Animal Behavior(马克斯·普朗克动物行为研究所);Technische Universität Dresden(德累斯顿工业大学);University of Sussex(萨塞克斯大学);Duke University(杜克大学)