{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T03:19:40Z","timestamp":1780456780946,"version":"3.54.1"},"reference-count":43,"publisher":"Informa UK Limited","issue":"2","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundatio","doi-asserted-by":"crossref","award":["2053746"],"award-info":[{"award-number":["2053746"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundatio","doi-asserted-by":"crossref","award":["DMS-2134209"],"award-info":[{"award-number":["DMS-2134209"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundatio","doi-asserted-by":"crossref","award":["ECCS-2328241"],"award-info":[{"award-number":["ECCS-2328241"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundatio","doi-asserted-by":"crossref","award":["OAC-2311848"],"award-info":[{"award-number":["OAC-2311848"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy (DOE) Office of Science Advanced Scientific Computing Research program","doi-asserted-by":"publisher","award":["DE-SC0023161"],"award-info":[{"award-number":["DE-SC0023161"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DOE\u2014Fusion Energy Science","award":["DE-SC0024583"],"award-info":[{"award-number":["DE-SC0024583"]}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational and Graphical Statistics"],"published-print":{"date-parts":[[2025,4,3]]},"DOI":"10.1080\/10618600.2024.2380051","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T15:25:15Z","timestamp":1721057115000},"page":"509-518","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":3,"title":["Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory"],"prefix":"10.1080","volume":"34","author":[{"given":"Jiajun","family":"Liang","sequence":"first","affiliation":[{"name":"ByteDance Inc","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Statistics, Purdue University","place":["West Lafayette"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Deng","sequence":"additional","affiliation":[{"name":"Machine Learning Research, Morgan Stanley","place":["New York"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qifan","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Statistics, Purdue University","place":["West Lafayette"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Mathematics & School of Mechanical Engineering, Purdue University","place":["West Lafayette"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,9,19]]},"reference":[{"key":"e_1_3_5_2_1","unstructured":"Akyildiz \u00d6. D. and Sabanis S. (2020) \u201cNonasymptotic Analysis of Stochastic Gradient Hamiltonian Monte Carlo under Local Conditions for Nonconvex Optimization \u201d arXiv preprint arXiv:2002.05465."},{"key":"e_1_3_5_3_1","first-page":"374","article-title":"\u201cTowards Federated Learning at Scale: System Design,\u201d","volume":"1","author":"Bonawitz K.","year":"2019","unstructured":"Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Kone\u010dn\u1ef3, J., Mazzocchi, S., and McMahan, B. (2019), \u201cTowards Federated Learning at Scale: System Design,\u201d Proceedings of Machine Learning and Systems, 1, 374\u2013388.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_5_4_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2"},{"key":"e_1_3_5_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2022.04.001"},{"key":"e_1_3_5_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3024629"},{"key":"e_1_3_5_7_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Chen T.","year":"2014","unstructured":"Chen, T., Fox, E., and Guestrin, C. (2014), \u201cStochastic Gradient Hamiltonian Monte Carlo,\u201d in International Conference on Machine Learning (ICML)."},{"key":"e_1_3_5_8_1","first-page":"1","article-title":"\u201cFast Mixing of Metropolized Hamiltonian Monte Carlo: Benefits of Multi-step Gradients,\u201d","volume":"21","author":"Chen Y.","year":"2020","unstructured":"Chen, Y., Dwivedi, R., Wainwright, M. J., and Yu, B. (2020b), \u201cFast Mixing of Metropolized Hamiltonian Monte Carlo: Benefits of Multi-step Gradients,\u201d Journal of Machine Learning Research, 21, 1\u201363.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_5_9_1","doi-asserted-by":"publisher","DOI":"10.4086\/toc.2022.v018a009"},{"key":"e_1_3_5_10_1","unstructured":"Cheng X. Chatterji N. S. Bartlett P. L. and Jordan M. I. (2018) \u201cUnderdamped Langevin MCMC: A Non-Asymptotic Analysis \u201d in Conference on Learning Theory (COLT)."},{"key":"e_1_3_5_11_1","unstructured":"Clanuwat T. Bober-Irizar M. Kitamoto A. Lamb A. Yamamoto K. and Ha D. (2018) \u201cDeep Learning for Classical Japanese Literature \u201d arXiv preprint arXiv:1812.01718."},{"key":"e_1_3_5_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12183"},{"key":"e_1_3_5_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2019.02.016"},{"key":"e_1_3_5_14_1","unstructured":"Deng W. Ma Y.-A. Song Z. Zhang Q. and Lin G. (2021) \u201cOn Convergence of Federated Averaging Langevin Dynamics \u201d arXiv preprint arXiv:2112.05120."},{"key":"e_1_3_5_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0370-2693(87)91197-X"},{"key":"e_1_3_5_16_1","volume-title":"Proceedings of Conference on Learning Theory (COLT)","author":"Erdogdu M. A.","year":"2021","unstructured":"Erdogdu, M. A., and Hosseinzadeh, R. (2021), \u201cOn the Convergence of Langevin Monte Carlo: the Interplay between Tail Growth and Smoothness,\u201d in Proceedings of Conference on Learning Theory (COLT)."},{"key":"e_1_3_5_17_1","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm10301"},{"key":"e_1_3_5_18_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429258411"},{"key":"e_1_3_5_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2010.00765.x"},{"key":"e_1_3_5_20_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Guo C.","year":"2017","unstructured":"Guo, C., Pleiss, G., Sun, Y., and Weinberger, K. Q. (2017), \u201cOn Calibration of Modern Neural Networks,\u201d in International Conference on Machine Learning (ICML)."},{"key":"e_1_3_5_21_1","first-page":"1","article-title":"\u201cDecentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo,\u201d","volume":"22","author":"G\u00fcrb\u00fczbalaban M.","year":"2021","unstructured":"G\u00fcrb\u00fczbalaban, M., Gao, X., Hu, Y., and Zhu, L. (2021), \u201cDecentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo,\u201d Journal of Machine Learning Research, 22, 1\u201369.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_5_22_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Karimireddy S. P.","year":"2020","unstructured":"Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S., Stich, S., and Suresh, A. T. (2020), \u201cScaffold: Stochastic Controlled Averaging for Federated Learning,\u201d in International Conference on Machine Learning (ICML)."},{"key":"e_1_3_5_23_1","unstructured":"Kone\u010dn\u1ef3 J. McMahan B. and Ramage D. (2015) \u201cFederated Optimization: Distributed Optimization Beyond the Datacenter \u201d arXiv preprint arXiv:1511.03575."},{"key":"e_1_3_5_24_1","unstructured":"Kone\u010dn\u1ef3 J. McMahan H. B. Yu F. X. Richtarik P. Suresh A. T. and Bacon D. (2016) \u201cFederated Learning: Strategies for Improving Communication Efficiency \u201d in NIPS Workshop on Private Multi-Party Machine Learning. Available at https:\/\/arxiv.org\/abs\/1610.05492."},{"key":"e_1_3_5_25_1","unstructured":"Krizhevsky A. and Hinton G. (2009) \u201cLearning Multiple Layers of Features from Tiny Images \u201d Technical Report University of Toronto ON Canada."},{"key":"e_1_3_5_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_3_5_27_1","volume-title":"Proceedings of the 3rd MLSys Conference.","author":"Li T.","year":"2020","unstructured":"Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., and Smithy, V. (2020b), \u201cFederated Optimization in Heterogeneous Networks,\u201d in Proceedings of the 3rd MLSys Conference."},{"key":"e_1_3_5_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101765"},{"key":"e_1_3_5_29_1","article-title":"\u201cA Complete Recipe for Stochastic Gradient MCMC,\u201d","volume":"28","author":"Ma Y.-A.","year":"2015","unstructured":"Ma, Y.-A., Chen, T., and Fox, E. (2015), \u201cA Complete Recipe for Stochastic Gradient MCMC,\u201d in Advances in Neural Information Processing Systems (NeurIPS) (Vol. 28).","journal-title":"in Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_5_30_1","article-title":"\u201cDimensionally Tight Running Time Bounds for Second-order Hamiltonian Monte Carlo,\u201d","author":"Mangoubi O.","year":"2018","unstructured":"Mangoubi, O., and Vishnoi, N. K. (2018), \u201cDimensionally Tight Running Time Bounds for Second-order Hamiltonian Monte Carlo,\u201d in Advances in Neural Information Processing Systems (NeurIPS).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_5_31_1","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"McMahan B.","year":"2017","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2017), \u201cCommunication-Efficient Learning of Deep Networks from Decentralized Data,\u201d in Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)."},{"key":"e_1_3_5_32_1","first-page":"113","volume-title":"Handbook of Markov Chain Monte Carlo","author":"Neal R. M.","year":"2012","unstructured":"Neal, R. M. (2012), \u201cMCMC Using Hamiltonian Dynamics,\u201d in Handbook of Markov Chain Monte Carlo, eds. S. Brooks, A. Gelman, G. L. Jones, X.-L. Meng (Vol. 54), pp. 113\u2013162, Boca Raton, FL: Chapman and Hall\/CRC."},{"key":"e_1_3_5_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1847120"},{"key":"e_1_3_5_34_1","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Plassier V.","year":"2023","unstructured":"Plassier, V., Moulines, E., and Durmus, A. (2023), \u201cFederated Averaging Langevin Dynamics: Toward a Unified Theory and New Algorithms,\u201d in Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)."},{"key":"e_1_3_5_35_1","volume-title":"Proceedings of Conference on Learning Theory (COLT)","author":"Raginsky M.","year":"2017","unstructured":"Raginsky, M., Rakhlin, A., and Telgarsky, M. (2017), \u201cNon-Convex Learning via Stochastic Gradient Langevin Dynamics: A Nonasymptotic Analysis,\u201d in Proceedings of Conference on Learning Theory (COLT)."},{"key":"e_1_3_5_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_3_5_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737464"},{"key":"e_1_3_5_38_1","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Vono M.","year":"2022","unstructured":"Vono, M., Plassier, V., Durmus, A., Dieuleveut, A., and \u00c9ric Moulines (2022), \u201cQLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning,\u201d in Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)."},{"key":"e_1_3_5_39_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wang H.","year":"2020","unstructured":"Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., and Khazaeni, Y. (2020), \u201cFederated Learning with Matched Averaging,\u201d in International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_5_40_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Welling M.","year":"2011","unstructured":"Welling, M., and Teh, Y. W. (2011), \u201cBayesian Learning via Stochastic Gradient Langevin Dynamics,\u201d in International Conference on Machine Learning (ICML)."},{"key":"e_1_3_5_41_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Zhu L.","year":"2019","unstructured":"Zhu, L., Liu, Z., and Han, S. (2019), \u201cDeep Leakage from Gradients,\u201d in Advances in Neural Information Processing Systems (NeurIPS) (Vol. 32)."},{"key":"e_1_3_5_42_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Zou D.","year":"2021","unstructured":"Zou, D., and Gu, Q. (2021), \u201cOn the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients,\u201d in International Conference on Machine Learning (ICML)."},{"key":"e_1_3_5_43_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Zou D.","year":"2019","unstructured":"Zou, D., Xu, P., and Gu, Q. (2019), \u201cStochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction,\u201d in Advances in Neural Information Processing Systems (NeurIPS) (Vol. 32)."},{"key":"e_1_3_5_44_1","volume-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI)","author":"Zou D.","year":"2021","unstructured":"Zou, D., Xu, P., and Gu, Q. (2021), \u201cFaster Convergence of Stochastic Gradient Langevin Dynamics for Non-log-concave Sampling,\u201d in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI)."}],"container-title":["Journal of Computational and Graphical Statistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/10618600.2024.2380051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:10:04Z","timestamp":1772813404000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/10618600.2024.2380051"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,19]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4,3]]}},"alternative-id":["10.1080\/10618600.2024.2380051"],"URL":"https:\/\/doi.org\/10.1080\/10618600.2024.2380051","relation":{},"ISSN":["1061-8600","1537-2715"],"issn-type":[{"value":"1061-8600","type":"print"},{"value":"1537-2715","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,19]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ucgs20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ucgs20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-06-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}