{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T20:10:36Z","timestamp":1788811836130,"version":"build-2803163510"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["52539005"],"award-info":[{"award-number":["52539005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Fundamental Research Program of Guangdong, China","award":["2023A1515011281"],"award-info":[{"award-number":["2023A1515011281"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"crossref","award":["202306150167"],"award-info":[{"award-number":["202306150167"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["24202107190000687"],"award-info":[{"award-number":["24202107190000687"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Foshan Science and Technology Research Project","award":["2220001018608"],"award-info":[{"award-number":["2220001018608"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tnnls.2026.3673350","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:39:45Z","timestamp":1773862785000},"page":"4726-4739","source":"Crossref","is-referenced-by-count":1,"title":["Sparse Variational Student-t Processes for Heavy-Tailed Modeling"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0350-5528","authenticated-orcid":false,"given":"Jian","family":"Xu","sequence":"first","affiliation":[{"name":"South China University of Technology","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7322-1873","authenticated-orcid":false,"given":"Delu","family":"Zeng","sequence":"additional","affiliation":[{"name":"South China University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4890-8230","authenticated-orcid":false,"given":"John","family":"Paisley","sequence":"additional","affiliation":[{"name":"Columbia University","place":["New York, NY, USA"],"department":["Department of Electrical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"55490","article-title":"Sparse inducing points in deep Gaussian processes: Enhancing modeling with denoising diffusion variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"ref3","first-page":"1959","article-title":"Learning unknown ODE models with Gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Heinonen"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-46147-8_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref6","first-page":"1168","article-title":"Trust your robots! Predictive uncertainty estimation of neural networks with sparse Gaussian processes","volume-title":"Proc. Conf. Robot Learn.","author":"Lee"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3583509"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3567297"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3596518"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612847"},{"key":"ref11","first-page":"877","article-title":"Student-t processes as alternatives to Gaussian processes","volume-title":"Proc. Artif. Intell. Statist.","author":"Shah"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/393"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04687-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/sjos.12611"},{"key":"ref15","first-page":"567","article-title":"Variational learning of inducing variables in sparse Gaussian processes","volume-title":"Proc. 12th Int. Conf. Artif. Intell. Statist.","author":"Titsias"},{"key":"ref16","first-page":"351","article-title":"Scalable variational Gaussian process classification","volume-title":"Proc. Artif. Intell. Statist.","author":"Hensman"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref18","article-title":"Gaussian processes for big data","author":"Hensman","year":"2013","journal-title":"arXiv:1309.6835"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref20","first-page":"885","article-title":"State space methods for efficient inference in student-t process regression","volume-title":"Proc. Artif. Intell. Statist.","author":"Solin"},{"key":"ref21","article-title":"Matrix inversion free variational inference in conditional student\u2019s t processes","volume-title":"Proc. 4th Symp. Adv. Approx. Bayesian Inference","author":"Popescu"},{"key":"ref22","volume":"28","author":"Amari","year":"2012","journal-title":"Differential-Geometrical Methods in Statistics"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0919-5_16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29549"},{"key":"ref25","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"Hoffman","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3619658"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4952"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BigData66926.2025.11402378"},{"key":"ref29","article-title":"Dequantified diffusion-Schr\u00f6dinger bridge for density ratio estimation","author":"Chen","year":"2025","journal-title":"arXiv:2505.05034"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29628"},{"issue":"9","key":"ref31","first-page":"1","article-title":"A multivariate student-t process model for dependent tail-weighted degradation data","volume":"57","author":"Xu","year":"2024","journal-title":"IISE Trans."},{"key":"ref32","first-page":"1","article-title":"Inverse methods for missing data imputation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01224"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.131438"},{"key":"ref35","article-title":"The elliptical processes: A family of fat-tailed stochastic processes","author":"B\u00e5nkestad","year":"2020","journal-title":"arXiv:2003.07201"},{"key":"ref36","article-title":"Variational elliptical processes","author":"B\u00e5nkestad","year":"2023","journal-title":"arXiv:2311.12566"},{"key":"ref37","first-page":"689","article-title":"Natural gradients in practice: Non-conjugate variational inference in Gaussian process models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Salimbeni"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s41884-018-0015-3"},{"key":"ref39","article-title":"Revisiting natural gradient for deep networks","author":"Pascanu","year":"2013","journal-title":"arXiv:1301.3584"},{"key":"ref40","first-page":"1646","article-title":"Sinkhorn natural gradient for generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Shen"},{"key":"ref41","first-page":"134151","article-title":"An improved empirical Fisher approximation for natural gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Woodland"},{"key":"ref42","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"2","key":"ref44","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","volume":"1","author":"Hu"},{"key":"ref45","first-page":"1861","article-title":"Probabilistic backpropagation for scalable learning of Bayesian neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hern\u00e1ndez-Lobato"},{"key":"ref46","first-page":"6515","article-title":"Sparse uncertainty representation in deep learning with inducing weights","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ritter"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2022.3155327"},{"key":"ref48","article-title":"Sparse Bayesian neural networks for regression: Tackling overfitting and computational challenges in uncertainty quantification","author":"Dabiran","year":"2023","journal-title":"arXiv:2310.15614"},{"key":"ref49","article-title":"Variational learning of Gaussian process latent variable models through stochastic gradient annealed importance sampling","author":"Xu","year":"2024","journal-title":"arXiv:2408.06710"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113187"},{"key":"ref51","first-page":"370","article-title":"Deep Kernel Learning","volume-title":"Proc. 19th Int. Conf. Artif. Intell. Statist.","author":"Wilson"},{"key":"ref52","article-title":"Bayesian Gaussian process odes via double normalizing flows","volume-title":"Proc. 28th Int. Conf. Artif. Intell. Statist.","author":"Xu"},{"key":"ref53","first-page":"5213","article-title":"Inducing point allocation for sparse Gaussian processes in high-throughput Bayesian optimisation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Moss"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3406635"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3435466"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1155"},{"key":"ref57","first-page":"884","article-title":"Random feature expansions for deep Gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cutajar"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020430"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA61862.2024.00189"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3163771"},{"key":"ref61","article-title":"Robust Bayesian optimization with student-t likelihood","author":"Martinez-Cantin","year":"2017","journal-title":"arXiv:1707.05729"},{"issue":"219","key":"ref62","first-page":"1","article-title":"Adagrad stepsizes: Sharp convergence over nonconvex landscapes","volume":"21","author":"Ward","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","article-title":"Incorporating Nesterov momentum into Adam","volume-title":"Proc. ICLR","author":"Dozat"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3373098"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511550683"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1017\/S095018430000029X"},{"issue":"1","key":"ref67","first-page":"30","article-title":"On the wallis formula","volume":"8","author":"Guo","year":"2015","journal-title":"Int. J. Anal. Appl."}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11676227\/11441992.pdf?arnumber=11441992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:20:20Z","timestamp":1788808820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11441992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":67,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2026.3673350","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}