{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:22:46Z","timestamp":1740165766295,"version":"3.37.3"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"National Basic Research Program 973 Program of China","award":["2013CB329403"],"award-info":[{"award-number":["2013CB329403"]}]},{"name":"National NSF of China","award":["61620106010","61322308","61332007"],"award-info":[{"award-number":["61620106010","61322308","61332007"]}]},{"name":"Youth Top-notch Talent Support Program Tiangong Institute for Intelligent Computing Tsinghua University"},{"name":"Collaborative Project with Tencent"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2017]]},"DOI":"10.1109\/tnnls.2017.2688499","type":"journal-article","created":{"date-parts":[[2017,6,28]],"date-time":"2017-06-28T18:08:32Z","timestamp":1498673312000},"page":"1-13","source":"Crossref","is-referenced-by-count":2,"title":["Learning Deep Generative Models With Doubly Stochastic Gradient MCMC"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1244-6336","authenticated-orcid":false,"given":"Chao","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Online algorithms and stochastic approximations","author":"bottou","year":"1998","journal-title":"Online Learning and Neural Networks"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref33","first-page":"1","article-title":"Variational inference for Monte Carlo objectives","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref32","article-title":"Reweighted wake-sleep","author":"bornschein","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","article-title":"Importance weighted autoencoders","author":"burda","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","first-page":"1971","article-title":"Doubly stochastic variational Bayes for non-conjugate inference","author":"titsias","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref36","first-page":"1242","article-title":"Deep AutoRegressive networks","author":"gregor","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref35","first-page":"29","article-title":"The neural autoregressive distribution estimator","author":"larochelle","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref34","first-page":"2629","article-title":"Neural adaptive sequential Monte Carlo","author":"gu","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"year":"2015","author":"goessling","journal-title":"Mixtures of sparse autoregressive networks","key":"ref60"},{"year":"2016","journal-title":"Theano A Python framework for fast computation of mathematical expressions","key":"ref62"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1162\/NECO_a_00397"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1126\/science.7761831"},{"key":"ref27","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1162\/089976602760128018"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref1","first-page":"226","article-title":"Deep generative stochastic networks trainable by backprop","author":"bengio","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref20","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref22","first-page":"1683","article-title":"Stochastic gradient Hamiltonian Monte Carlo","author":"chen","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref21","first-page":"1","article-title":"Bayesian posterior sampling via stochastic gradient Fisher scoring","author":"ahn","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref24","first-page":"1791","article-title":"Neural variational inference and learning in belief networks","author":"mnih","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref23","first-page":"3203","article-title":"Bayesian sampling using stochastic gradient thermostats","author":"ding","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/TNNLS.2016.2599820"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/TNNLS.2015.2499302"},{"key":"ref50","first-page":"1137","article-title":"Evaluating probabilities under high-dimensional latent variable models","author":"murray","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/5.726791"},{"key":"ref59","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3348.001.0001","author":"frey","year":"1998","journal-title":"Graphical Models for Machine Learning and Digital Communication"},{"key":"ref58","first-page":"325","article-title":"Iterative neural autoregressive distribution estimator NADE-k","author":"raiko","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","first-page":"467","article-title":"A deep and tractable density estimator","author":"uria","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref56","first-page":"1","article-title":"The variational Gaussian process","author":"tran","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref55","first-page":"3738","article-title":"Ladder variational autoencoders","author":"s\u00f8nderby","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","first-page":"1177","article-title":"Learning to generate with memory","author":"li","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref53","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","author":"gregor","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref52","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"van den oord","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref10","first-page":"268","article-title":"Learning deep sigmoid belief networks with data augmentation","author":"gan","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref11","first-page":"1","article-title":"Learning the structure of deep sparse graphical models","author":"adams","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"year":"2013","author":"owen","journal-title":"Monte Carlo Theory Methods and Examples","key":"ref40"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1023\/A:1007665907178"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1613\/jair.251","article-title":"Mean field theory for sigmoid belief networks","volume":"4","author":"saul","year":"1996","journal-title":"J Artif Intell Res"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/978-1-4757-4145-2"},{"key":"ref15","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref16","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref17","first-page":"814","article-title":"Black box variational inference","author":"ranganath","year":"2014","journal-title":"Proc 17th Int Conf Artif Intell Statist"},{"key":"ref18","first-page":"1795","article-title":"High-order stochastic gradient thermostats for Bayesian learning of deep models","author":"li","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref19","first-page":"1823","article-title":"Scalable deep poisson factor analysis for topic modeling","author":"gan","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1038\/nature14236"},{"key":"ref5","first-page":"801","article-title":"Dynamic pooling and unfolding recursive autoencoders for paraphrase detection","author":"socher","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref7","first-page":"448","article-title":"Deep Boltzmann machines","author":"salakhutdinov","year":"2009","journal-title":"Proc 12th Int Conf Artif Intell Statist"},{"key":"ref49","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"year":"1995","author":"neal","article-title":"Bayesian learning for neural networks","key":"ref9"},{"key":"ref46","first-page":"400","article-title":"Modeling high-dimensional discrete data with multi-layer neural networks","author":"bengio","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"2526","article-title":"One-shot learning by inverting a compositional causal process","author":"lake","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref47","first-page":"1","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1145\/1390156.1390266"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1016\/0004-3702(92)90065-6"},{"year":"2013","author":"lichman","journal-title":"UCI Machine Learning Repository","key":"ref44"},{"key":"ref43","first-page":"509","article-title":"Inductive principles for restricted Boltzmann machine learning","author":"marlin","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/6104215\/07961239.pdf?arnumber=7961239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:25:48Z","timestamp":1642004748000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7961239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tnnls.2017.2688499","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2017]]}}}