We propose a relative entropy gradient sampler (REGS) for sampling from unnormalized distributions. REGS is a particle method that seeks a sequence of simple nonlinear transforms iteratively pushing the initial samples from a reference distribution into the samples from an unnormalized target distribution. To determine the nonlinear transforms at each iteration, we consider the Wasserstein gradient flow of relative entropy. This gradient flow determines a path of probability distributions that interpolates the reference distribution and the target distribution. It is characterized by an ODE system with velocity fields depending on the density ratios of the density of evolving particles and the unnormalized target density. To sample with REGS, we need to estimate the density ratios and simulate the ODE system with particle evolution. We propose a novel nonparametric approach to estimating the logarithmic density ratio using neural networks. Extensive simulation studies on challenging multimodal 1D and 2D mixture distributions and Bayesian logistic regression on real datasets demonstrate that the REGS outperforms the state-of-the-art sampling methods included in the comparison.
Contrastive Bayesian Inference for Unnormalized Models
Graduate School of Economics, Keio University(庆应义塾大学经济学研究科);Faculty of Economics, Keio University(庆应义塾大学经济学部);The Institute of Statistical Mathematics(统计数学研究所);Graduate School of Information Science and Technology, The University of Tokyo(东京大学信息理工学系研究科);RIKEN Center for Brain Science(理化学脑科学研究中心)
A Neural Network MCMC sampler that maximizes Proposal Entropy
Redwood Center for theoretical Neuroscience(雷德伍德理论神经科学中心);Department of Physics(物理系);University of California Berkeley(加州大学伯克利分校);Berkeley AI Research(伯克利人工智能研究中心);Helen Wills Neuroscience Institute(海伦·威尔斯神经科学研究所)
Department of Computer Science, Aalto University, Finland(阿姆斯特丹大学计算机科学系,芬兰);Department of Engineering, University of Cambridge, United Kingdom(剑桥大学工程系,英国);Department of Empirical Inference, Max Planck Institute for Intelligent Systems, Tübingen, Germany(智能系统研究所经验推断系,德国)
Improved off-policy training of diffusion samplers
Mila, Université de Montréal(米拉-蒙特利尔大学);Jagiellonian University(雅盖隆大学);KAIST(韩国科学技术院);Ciela Institute(塞拉研究所);Dreamfold(德里姆福尔德公司);CIFAR(加拿大高级研究院);University of Edinburgh(爱丁堡大学)
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Mila – Québec AI Institute(米拉-魁北克人工智能研究所);McGill University(麦吉尔大学);Dreamfold;Université de Montréal(蒙特利尔大学);University of Oxford(牛津大学);Ciela Institute(Ciela研究所);Center for Computational Astrophysics, Flatiron Institute(弗拉铁隆研究所计算天体物理中心);Jagiellonian University(雅盖隆大学);CIFAR(加拿大高级研究所)
University of Cambridge(剑桥大学);Zuse Institute Berlin(柏林图灵研究所);dida Datenschmiede GmbH(dida数据安全公司);NVIDIA(NVIDIA公司);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);California Institute of Technology(加州理工学院)
Entropy-Guided Sampling of Flat Modes in Discrete Spaces
Department of Computer Science, College of Science & College of Engineering, Purdue University(计算机科学系、科学与工程学院、普渡大学);Department of Biostatistics & Bioinformatics, Duke University School of Medicine, Duke University(生物统计学与生物信息学系、杜克大学医学学院、杜克大学)