{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:01:09Z","timestamp":1771455669918,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319684444","type":"print"},{"value":"9783319684451","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-68445-1_53","type":"book-chapter","created":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T20:40:36Z","timestamp":1508791236000},"page":"451-459","source":"Crossref","is-referenced-by-count":8,"title":["Natural Langevin Dynamics for Neural Networks"],"prefix":"10.1007","author":[{"given":"Ga\u00e9tan","family":"Marceau-Caron","sequence":"first","affiliation":[]},{"given":"Yann","family":"Ollivier","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,10,24]]},"reference":[{"key":"53_CR1","unstructured":"Ahn, S., Korattikara, A., Welling, M.: Bayesian posterior sampling via stochastic gradient Fisher scoring. In: ICML (2012)"},{"key":"53_CR2","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"S Amari","year":"1998","unstructured":"Amari, S.: Natural gradient works efficiently in learning. Neural Comput. 10, 251\u2013276 (1998)","journal-title":"Neural Comput."},{"key":"53_CR3","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)"},{"key":"53_CR4","unstructured":"Bottou, L., LeCun, Y.: Large scale online learning. In: NIPS, vol. 30, p. 77 (2003)"},{"key":"53_CR5","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/978-3-7908-2604-3_16","volume-title":"Proceedings of COMPSTAT 2010","author":"L Bottou","year":"2010","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. Proceedings of COMPSTAT 2010, pp. 177\u2013186. Springer, Heidelberg (2010)"},{"key":"53_CR6","unstructured":"Chen, C., Ding, N., Carin, L.: On the convergence of stochastic gradient MCMC algorithms with high-order integrators. In: Advances in Neural Information Processing Systems, pp. 2278\u20132286 (2015)"},{"key":"53_CR7","unstructured":"Durmus, A., Moulines, E.: High-dimensional Bayesian inference via the unadjusted Langevin algorithm. arXiv preprint \narXiv:1605.01559\n\n (2016)"},{"key":"53_CR8","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)"},{"issue":"2","key":"53_CR9","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1111\/j.1467-9868.2010.00765.x","volume":"73","author":"M Girolami","year":"2011","unstructured":"Girolami, M., Calderhead, B.: Riemann manifold langevin and hamiltonian monte carlo methods. J. Roy. Stat. Soc. Series B (Statistical Methodology) 73(2), 123\u2013214 (2011)","journal-title":"J. Roy. Stat. Soc. Series B (Statistical Methodology)"},{"key":"53_CR10","unstructured":"Li, C., Chen, C., Carlson, D.E., Carin, L.: Preconditioned stochastic gradient Langevin dynamics for deep neural networks. In: Schuurmans, D., Wellman, M.P. (eds.) Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 12\u201317 February 2016, Phoenix, Arizona, USA, pp. 1788\u20131794. AAAI Press (2016)"},{"issue":"3","key":"53_CR11","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1162\/neco.1992.4.3.448","volume":"4","author":"DJC MacKay","year":"1992","unstructured":"MacKay, D.J.C.: A practical Bayesian framework for backpropagation networks. Neural Comput. 4(3), 448\u2013472 (1992)","journal-title":"Neural Comput."},{"key":"53_CR12","volume-title":"Information Theory, Inference and Learning Algorithms","author":"DJC MacKay","year":"2003","unstructured":"MacKay, D.J.C.: Information Theory, Inference and Learning Algorithms. Cambridge University Press, Cambridge (2003)"},{"key":"53_CR13","unstructured":"Majewski, S., Durmus, A., Miasojedow, B.: (2017)"},{"key":"53_CR14","unstructured":"Marceau-Caron, G., Ollivier, Y.: Practical Riemannian neural networks. arXiv, abs\/1602.08007 (2016)"},{"key":"53_CR15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0745-0","volume-title":"Bayesian Learning for Neural Networks","author":"RM Neal","year":"1996","unstructured":"Neal, R.M.: Bayesian Learning for Neural Networks. Springer, New York (1996)"},{"issue":"2","key":"53_CR16","first-page":"108","volume":"4","author":"Y Ollivier","year":"2015","unstructured":"Ollivier, Y.: Riemannian metrics for neural networks I: feedforward networks. Inf. Infer. 4(2), 108\u2013153 (2015)","journal-title":"Inf. Infer."},{"key":"53_CR17","unstructured":"Pascanu, R., Bengio, Y.: Natural gradient revisited. arXiv, abs\/1301.3584 (2013)"},{"key":"53_CR18","unstructured":"Patterson, S., Teh, Y.W.: Stochastic gradient Riemannian Langevin dynamics on the probability simplex. In: Advances in Neural Information Processing Systems, pp. 3102\u20133110 (2013)"},{"issue":"1","key":"53_CR19","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"issue":"7","key":"53_CR20","first-page":"1","volume":"17","author":"YW Teh","year":"2016","unstructured":"Teh, Y.W., Thiery, A.H., Vollmer, S.J.: Consistency and fluctuations for stochastic gradient Langevin dynamics. J. Mach. Learn. Res. 17(7), 1\u201333 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"53_CR21","volume-title":"Asymptotic Statistics","author":"AW Vaart van der","year":"2000","unstructured":"van der Vaart, A.W.: Asymptotic Statistics. Cambridge University Press, Cambridge (2000)"},{"key":"53_CR22","unstructured":"Welling, M., Teh, Y.W.: Bayesian learning via stochastic gradient Langevin dynamics. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 681\u2013688 (2011)"},{"key":"53_CR23","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.spl.2014.04.002","volume":"91","author":"T Xifara","year":"2014","unstructured":"Xifara, T., Sherlock, C., Livingstone, S., Byrne, S., Girolami, M.: Langevin diffusions and the Metropolis-adjusted Langevin algorithm. Stat. Probab. Lett. 91, 14\u201319 (2014)","journal-title":"Stat. Probab. Lett."}],"container-title":["Lecture Notes in Computer Science","Geometric Science of Information"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-68445-1_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,24]],"date-time":"2017-10-24T19:32:12Z","timestamp":1508873532000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-68445-1_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319684444","9783319684451"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-68445-1_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}