{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:23:26Z","timestamp":1758126206082,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"OP VVV","award":["Research Center for Informatics"],"award-info":[{"award-number":["Research Center for Informatics"]}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s10994-023-06345-6","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T23:02:51Z","timestamp":1687302171000},"page":"2791-2819","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo"],"prefix":"10.1007","volume":"112","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2229-8824","authenticated-orcid":false,"given":"Vyacheslav","family":"Kungurtsev","sequence":"first","affiliation":[]},{"given":"Adam","family":"Cobb","sequence":"additional","affiliation":[]},{"given":"Tara","family":"Javidi","sequence":"additional","affiliation":[]},{"given":"Brian","family":"Jalaian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"6345_CR1","unstructured":"Akyildiz, \u00d6.D., & Sabanis, S. (2020). Nonasymptotic analysis of stochastic gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization. arXiv preprint arXiv:2002.05465."},{"issue":"8","key":"6345_CR2","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1109\/TAC.2018.2880407","volume":"64","author":"AS Berahas","year":"2018","unstructured":"Berahas, A. S., Bollapragada, R., Keskar, N. S., & Wei, E. (2018). Balancing communication and computation in distributed optimization. IEEE Transactions on Automatic Control, 64(8), 3141\u20133155.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"6345_CR3","unstructured":"Betancourt, M. (2015). The fundamental incompatibility of Hamiltonian Monte Carlo and data subsampling. arXiv preprint arXiv:1502.01510."},{"issue":"3","key":"6345_CR4","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1214\/19-AAP1528","volume":"30","author":"N Bou-Rabee","year":"2020","unstructured":"Bou-Rabee, N., Eberle, A., & Zimmer, R. (2020). Coupling and convergence for Hamiltonian Monte Carlo. The Annals of applied probability, 30(3), 1209\u20131250.","journal-title":"The Annals of applied probability"},{"key":"6345_CR5","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.spa.2022.04.001","volume":"149","author":"HN Chau","year":"2022","unstructured":"Chau, H. N., & R\u00e1sonyi, M. (2022). Stochastic gradient Hamiltonian Monte Carlo for non-convex learning. Stochastic Processes and their Applications, 149, 341\u2013368.","journal-title":"Stochastic Processes and their Applications"},{"key":"6345_CR6","unstructured":"Chen, T., Fox, E., & Guestrin, C. (2014). Stochastic gradient Hamiltonian Monte Carlo. In: International Conference on Machine Learning, pp. 1683\u20131691. PMLR."},{"issue":"68","key":"6345_CR7","first-page":"1","volume":"21","author":"X Chen","year":"2020","unstructured":"Chen, X., Du, S. S., & Tong, X. T. (2020). On stationary-point hitting time and ergodicity of stochastic gradient Langevin dynamics. Journal of Machine Learning Research, 21(68), 1\u201341.","journal-title":"Journal of Machine Learning Research"},{"key":"6345_CR8","unstructured":"Cobb, A.D., & Jalaian, B. (2020). Scaling Hamiltonian Monte Carlo inference for Bayesian neural networks with symmetric splitting. arXiv preprint arXiv:2010.06772."},{"issue":"2","key":"6345_CR9","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1109\/TSIPN.2016.2524588","volume":"2","author":"P Di Lorenzo","year":"2016","unstructured":"Di Lorenzo, P., & Scutari, G. (2016). Next: In-network nonconvex optimization. IEEE Transactions on Signal and Information Processing over Networks, 2(2), 120\u2013136.","journal-title":"IEEE Transactions on Signal and Information Processing over Networks"},{"key":"6345_CR10","unstructured":"Durmus, A., Moulines, E., & Saksman, E. (2017). On the convergence of Hamiltonian Mmonte Carlo. arXiv preprint arXiv:1705.00166."},{"issue":"4A","key":"6345_CR11","doi-asserted-by":"publisher","first-page":"2854","DOI":"10.3150\/18-BEJ1073","volume":"25","author":"A Durmus","year":"2019","unstructured":"Durmus, A., & Moulines, E. (2019). High-dimensional bayesian inference via the unadjusted langevin algorithm. Bernoulli, 25(4A), 2854\u20132882.","journal-title":"Bernoulli"},{"key":"6345_CR12","doi-asserted-by":"publisher","first-page":"2931","DOI":"10.1287\/opre.2021.2162","volume":"70","author":"X Gao","year":"2021","unstructured":"Gao, X., G\u00fcrb\u00fczbalaban, M., & Zhu, L. (2021). Global convergence of stochastic gradient Hamiltonian Monte Carlo for nonconvex stochastic optimization: nonasymptotic performance bounds and momentum-based acceleration. Operations Research, 70, 2931\u20132947.","journal-title":"Operations Research"},{"key":"6345_CR13","unstructured":"G\u00fcrb\u00fczbalaban, M., Gao, X., Hu, Y., & Zhu, L. (2020). Decentralized stochastic gradient Langevin dynamics and Hamiltonian Monte Carlo. arXiv preprint arXiv:2007.00590."},{"issue":"1","key":"6345_CR14","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/0095-0696(78)90006-2","volume":"5","author":"D Harrison Jr","year":"1978","unstructured":"Harrison, D., Jr., & Rubinfeld, D. L. (1978). Hedonic housing prices and the demand for clean air. Journal of Environmental Economics and Management, 5(1), 81\u2013102.","journal-title":"Journal of Environmental Economics and Management"},{"key":"6345_CR15","unstructured":"Hsieh, C.-J., Si, S., & Dhillon, I. (2014). A divide-and-conquer solver for kernel support vector machines. In International Conference on Machine Learning, pp. 566\u2013574. PMLR."},{"key":"6345_CR16","unstructured":"Izmailov, P., Vikram, S., Hoffman, M.D., & Wilson, A.G. (2021). What are Bayesian neural network posteriors really like? arXiv preprint arXiv:2104.14421"},{"key":"6345_CR17","unstructured":"Kolesov, A., & Kungurtsev, V. (2021). Decentralized langevin dynamics over a directed graph. arXiv preprint arXiv:2103.05444."},{"key":"6345_CR18","unstructured":"Kungurtsev, V. (2020). Stochastic gradient langevin dynamics on a distributed network. arXiv preprint arXiv:2001.00665."},{"key":"6345_CR19","unstructured":"Lalitha, A., Wang, X., Kilinc, O., Lu, Y., Javidi, T., & Koushanfar, F. (2019). Decentralized Bayesian learning over graphs. arXiv preprint arXiv:1905.10466."},{"issue":"11","key":"6345_CR20","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"6345_CR21","unstructured":"Mesquita, D., Blomstedt, P., & Kaski, S. (2020). Embarrassingly parallel MCMC using deep invertible transformations. In Uncertainty in Artificial Intelligence, pp. 1244\u20131252. PMLR."},{"key":"6345_CR22","first-page":"15978","volume":"33","author":"A Parayil","year":"2020","unstructured":"Parayil, A., Bai, H., George, J., & Gurram, P. (2020). Decentralized Langevin dynamics for Bayesian learning. Advances in Neural Information Processing Systems, 33, 15978\u201315989.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6345_CR23","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s10107-020-01487-0","volume":"187","author":"S Pu","year":"2020","unstructured":"Pu, S., & Nedi\u0107, A. (2020). Distributed stochastic gradient tracking methods. Mathematical Programming, 187, 409\u2013457.","journal-title":"Mathematical Programming"},{"issue":"4","key":"6345_CR24","doi-asserted-by":"publisher","first-page":"341","DOI":"10.2307\/3318418","volume":"2","author":"GO Roberts","year":"1996","unstructured":"Roberts, G. O., Tweedie, R. L., et al. (1996). Exponential convergence of Langevin distributions and their discrete approximations. Bernoulli, 2(4), 341\u2013363.","journal-title":"Bernoulli"},{"key":"6345_CR25","unstructured":"Shoham, N., Avidor, T., Keren, A., Israel, N., Benditkis, D., Mor-Yosef, L., & Zeitak, I. (2019). Overcoming forgetting in federated learning on non-iid data. arXiv preprint arXiv:1910.07796."},{"key":"6345_CR26","first-page":"1","volume":"17","author":"YW Teh","year":"2016","unstructured":"Teh, Y. W., Thiery, A. H., & Vollmer, S. J. (2016). Consistency and fluctuations for stochastic gradient Langevin dynamics. Journal of Machine Learning Research, 17, 1\u201333.","journal-title":"Journal of Machine Learning Research"},{"key":"6345_CR27","unstructured":"Welling, M., & Teh, Y.W. (2011). Bayesian learning via stochastic gradient Langevin dynamics. In Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 681\u2013688. Citeseer."},{"key":"6345_CR28","unstructured":"Zhang, Y., Liang, P., & Charikar, M. (2017). A hitting time analysis of stochastic gradient Langevin dynamics. In Conference on Learning Theory, pp. 1980\u20132022. PMLR."},{"key":"6345_CR29","unstructured":"Zou, D., & Gu, Q. (2021). On the convergence of Hamiltonian Monte Carlo with stochastic gradients. In International Conference on Machine Learning, pp. 13012\u201313022. PMLR."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06345-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06345-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06345-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:03:01Z","timestamp":1718841781000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06345-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,20]]},"references-count":29,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["6345"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06345-6","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2023,6,20]]},"assertion":[{"value":"17 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts"}},{"value":"The authors believe there are no potential ethical considerations with this work.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"All authors consent to the process of review and publication of the entire manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate and publish"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}