Though with progress, model learning and performing posterior inference still remains a common challenge for using deep generative models, especially for handling discrete hidden variables. This paper is mainly concerned with algorithms for learning Helmholz machines, which is characterized by pairing the generative model with an auxiliary inference model. A common drawback of previous learning algorithms is that they indirectly optimize some bounds of the targeted marginal log-likelihood. In contrast, we successfully develop a new class of algorithms, based on stochastic approximation (SA) theory of the Robbins-Monro type, to directly optimize the marginal log-likelihood and simultaneously minimize the inclusive KL-divergence. The resulting learning algorithm is thus called joint SA (JSA). Moreover, we construct an effective MCMC operator for JSA. Our results on the MNIST datasets demonstrate that the JSA's performance is consistently superior to that of competing algorithms like RWS, for learning a range of difficult models.
Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation
Rice University（莱斯大学）；Shimane University（岛根大学）；Team Makutu TotalEnergies（Team Makutu道达尔能源公司）；Inria Bordeaux（波尔多信息与自动化研究所）；University of Pau and Pays de l'Adour（波城与阿杜尔地区大学）；McMaster University（麦克马斯特大学）；the Vector Institute（向量研究所）；Purdue University（普渡大学）
Inference for stochastic kinetic models from multiple data sources for joint estimation of infection dynamics from aggregate reports and virological data
Inference for stochastic kinetic models from multiple data sources for joint estimation of infection dynamics from aggregate reports and virological data
A Green-Integral-Constrained Neural Solver with Stochastic Physics-Informed Regularization
University of the Basque Country (UPV/EHU)（巴斯克国家大学）；Basque Center for Applied Mathematics (BCAM)（巴斯克应用数学中心）；Ikerbasque, Basque Foundation for Science（Ikerbasque巴斯克科学基金会）；King Abdullah University of Science and Technology (KAUST)（卡迪斯国王科学与技术大学）
Neural-network solutions to stochastic reaction networks
Beijing Normal University（北京师范大学）；Institute of Theoretical Physics, Chinese Academy of Sciences（中国科学院理论物理研究所）；Hangzhou Institute for Advanced Study, UCAS（中国科学院大学杭州高等研究院）；International Centre for Theoretical Physics Asia-Pacific（亚太国际理论物理中心）
