{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T01:11:52Z","timestamp":1754183512609,"version":"3.41.2"},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2025,8,1]]},"DOI":"10.1587\/transinf.2024edp7235","type":"journal-article","created":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T17:12:59Z","timestamp":1739985179000},"page":"991-1000","source":"Crossref","is-referenced-by-count":0,"title":["A Quasi-Newton Method for a Mean Variance Estimation Network"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Seiya","family":"SATOH","sequence":"first","affiliation":[{"name":"Tokyo Denki University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"doi-asserted-by":"crossref","unstructured":"[1] D.A. Nix and A.S. Weigend, \u201cEstimating the mean and variance of the target probability distribution,\u201d Proc. IEEE International Conf. Neural Networks \u201994, pp.55-60, IEEE, 1994. DOI: 10.1109\/ICNN.1994.374138. 10.1109\/icnn.1994.374138","key":"1","DOI":"10.1109\/ICNN.1994.374138"},{"doi-asserted-by":"publisher","unstructured":"[2] P.K. Han, W.M. Klein, and N.K. Arora, \u201cVarieties of uncertainty in health care: a conceptual taxonomy,\u201d Medical Decision Making, vol.31, no.6, pp.828-838, 2011. DOI: 10.1177\/0272989X11393976. 10.1177\/0272989x11393976","key":"2","DOI":"10.1177\/0272989X11393976"},{"doi-asserted-by":"publisher","unstructured":"[3] G. Segal, I. Shaliastovich, and A. Yaron, \u201cGood and bad uncertainty: Macroeconomic and financial market implications,\u201d Journal of Financial Economics, vol.117, no.2, pp.369-397, 2015. 10.1016\/j.jfineco.2015.05.004","key":"3","DOI":"10.1016\/j.jfineco.2015.05.004"},{"doi-asserted-by":"publisher","unstructured":"[4] K. Jurado, S.C. Ludvigson, and S. Ng, \u201cMeasuring uncertainty,\u201d American Economic Review, vol.105, no.3, pp.1177-1216, 2015. 10.1257\/aer.20131193","key":"4","DOI":"10.1257\/aer.20131193"},{"doi-asserted-by":"crossref","unstructured":"[5] E. Patelli, R. Ghanem, D. Higdon, and H. Owhadi, \u201cCOSSAN: A multidisciplinary software suite for uncertainty quantification and risk management,\u201d Handbook of Uncertainty Quantification, pp.1-69, 2016. DOI: 10.1007\/978-3-319-12385-1_59. 10.1007\/978-3-319-12385-1_59","key":"5","DOI":"10.1007\/978-3-319-11259-6_59-1"},{"doi-asserted-by":"publisher","unstructured":"[6] F. Goerlandt and G. Reniers, \u201cOn the assessment of uncertainty in risk diagrams,\u201d Safety Science, vol.84, pp.67-77, 2016. DOI: 10.1016\/j.ssci.2015.12.001. 10.1016\/j.ssci.2015.12.001","key":"6","DOI":"10.1016\/j.ssci.2015.12.001"},{"doi-asserted-by":"publisher","unstructured":"[7] J. Irvin, P. Rajpurkar, M. Ko, Y. Yu, S. Ciurea-Ilcus, C. Chute, H. Marklund, B. Haghgoo, R. Ball, K. Shpanskaya, J. Seekins, D.A. Mong, S.S. Halabi, J.K. Sandberg, R. Jones, D.B. Larson, C.P. Langlotz, B.N. Patel, M.P. Lungren, and A.Y. Ng, \u201cCheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison,\u201d Proc. AAAI Conf. Artificial Intelligence, vol.33, no.1, pp.590-597, 2019. DOI: 10.1609\/aaai.v33i01.3301590. 10.1609\/aaai.v33i01.3301590","key":"7","DOI":"10.1609\/aaai.v33i01.3301590"},{"doi-asserted-by":"publisher","unstructured":"[8] L. Sluijterman, E. Cator, and T. Heskes, \u201cOptimal training of Mean Variance Estimation neural networks,\u201d Neurocomputing, vol.597, no.127929, 2024. DOI: 10.1016\/j.neucom.2024.127929. 10.1016\/j.neucom.2024.127929","key":"8","DOI":"10.1016\/j.neucom.2024.127929"},{"unstructured":"[9] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014. DOI: 10.48550\/arXiv.1412.6980. 10.48550\/arXiv.1412.6980","key":"9"},{"doi-asserted-by":"publisher","unstructured":"[10] A. Shrestha and A. Mahmood, \u201cReview of deep learning algorithms and architectures,\u201d IEEE Access, vol.7, pp.53040-53065, 2019. DOI: 10.1109\/ACCESS.2019.2912200. 10.1109\/access.2019.2912200","key":"10","DOI":"10.1109\/ACCESS.2019.2912200"},{"unstructured":"[11] L. Yuan, D. Chen, Y.L. Chen, N. Codella, X. Dai, J. Gao, H. Hu, X. Huang, B. Li, C. Li, C. Liu, M. Liu, Z. Liu, Y. Lu, Y. Shi, L. Wang, J. Wang, B. Xiao, Z. Xiao, J. Yang, M. Zeng, L. Zhou, and P. Zhang, \u201cFlorence: A new foundation model for computer vision,\u201d arXiv preprint arXiv:2111.11432, 2021. DOI: 10.48550\/arXiv.2111.11432. 10.48550\/arXiv.2111.11432","key":"11"},{"unstructured":"[12] A. Kumar, O. Irsoy, P. Ondruska, M. Iyyer, J. Bradbury, I. Gulrajani, V. Zhong, R. Paulus, and R. Socher, \u201cAsk me anything: Dynamic memory networks for natural language processing,\u201d Proc. 33rd International Conf. Machine Learning, pp.1378-1387, PMLR, 2016.","key":"12"},{"unstructured":"[13] I. Bello, B. Zoph, V. Vasudevan, and Q.V. Le, \u201cNeural optimizer search with reinforcement learning,\u201d Proc. 34th International Conf. Machine Learning, pp.459-468, PMLR, 2017.","key":"13"},{"unstructured":"[14] J. Martens et al., \u201cDeep learning via Hessian-free optimization.,\u201d Proc. 27th International Conf. Machine Learning, pp.735-742, PMLR, 2010.","key":"14"},{"unstructured":"[15] J. Sohl-Dickstein, B. Poole, and S. Ganguli, \u201cFast large-scale optimization by unifying stochastic gradient and quasi-Newton methods,\u201d Proc. 31st International Conf. Machine Learning, pp.604-612, PMLR, 2014.","key":"15"},{"doi-asserted-by":"publisher","unstructured":"[16] Z. Yao, A. Gholami, S. Shen, M. Mustafa, K. Keutzer, and M. Mahoney, \u201cADAHESSIAN: An adaptive second order optimizer for machine learning,\u201d Proc. AAAI Conf. Artificial Intelligence, pp.10665-10673, 2021. DOI: 10.1609\/aaai.v35i12.17275. 10.1609\/aaai.v35i12.17275","key":"16","DOI":"10.1609\/aaai.v35i12.17275"},{"unstructured":"[17] R. Fletcher, Practical methods of optimization, 2nd edition, JOHN WILEY &amp; SONS, 1987.","key":"17"},{"doi-asserted-by":"publisher","unstructured":"[18] C.G. Broyden, \u201cThe convergence of a class of double-rank minimization algorithms: 2. the new algorithm,\u201d IMA Journal of Applied Mathematics, vol.6, no.3, pp.222-231, 1970. DOI: 10.1093\/imamat\/6.3.222. 10.1093\/imamat\/6.3.222","key":"18","DOI":"10.1093\/imamat\/6.3.222"},{"doi-asserted-by":"publisher","unstructured":"[19] R. Fletcher, \u201cA new approach to variable metric algorithms,\u201d The Computer Journal, vol.13, no.3, pp.317-322, 1970. DOI: 10.1093\/comjnl\/13.3.317. 10.1093\/comjnl\/13.3.317","key":"19","DOI":"10.1093\/comjnl\/13.3.317"},{"doi-asserted-by":"publisher","unstructured":"[20] D. Goldfarb, \u201cA family of variable-metric methods derived by variational means,\u201d Mathematics of Computation, vol.24, no.109, pp.23-26, 1970. DOI: 10.1090\/S0025-5718-1970-0258249-6. 10.1090\/s0025-5718-1970-0258249-6","key":"20","DOI":"10.1090\/S0025-5718-1970-0258249-6"},{"doi-asserted-by":"publisher","unstructured":"[21] D.F. Shanno, \u201cConditioning of quasi-Newton methods for function minimization,\u201d Mathematics of Computation, vol.24, no.111, pp.647-656, 1970. DOI: 10.1090\/S0025-5718-1970-0274029-X. 10.1090\/s0025-5718-1970-0274029-x","key":"21","DOI":"10.1090\/S0025-5718-1970-0274029-X"},{"unstructured":"[23] D.A. Clevert, T. Unterthiner, and S. Hochreiter, \u201cFast and accurate deep network learning by exponential linear units (ELUs),\u201d arXiv preprint arXiv:1511.07289, 2015. DOI: 10.48550\/arXiv.1511.07289. 10.48550\/arXiv.1511.07289","key":"22"},{"doi-asserted-by":"crossref","unstructured":"[24] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDelving deep into rectifiers: Surpassing human-level performance on imagenet classification,\u201d Proc. IEEE International Conf. Computer Vision, pp.1026-1034, 2015. DOI: 10.1109\/ICCV.2015.123. 10.1109\/iccv.2015.123","key":"23","DOI":"10.1109\/ICCV.2015.123"},{"unstructured":"[25] J.M. Hern\u00e1ndez-Lobato and R. Adams, \u201cProbabilistic backpropagation for scalable learning of Bayesian neural networks,\u201d Proc. 32nd International Conf. Machine Learning, pp.1861-1869, PMLR, 2015.","key":"24"},{"unstructured":"[26] Y. Gal and Z. Ghahramani, \u201cDropout as a Bayesian approximation: Representing model uncertainty in deep learning,\u201d Proc. 33rd International Conf. Machine Learning, pp.1050-1059, PMLR, 2016.","key":"25"},{"unstructured":"[27] B. Lakshminarayanan, A. Pritzel, and C. Blundell, \u201cSimple and scalable predictive uncertainty estimation using deep ensembles,\u201d Proc. Advances in Neural Information Processing Systems, 2017.","key":"26"},{"unstructured":"[28] T. Pearce, A. Brintrup, M. Zaki, and A. Neely, \u201cHigh-quality prediction intervals for deep learning: A distribution-free, ensembled approach,\u201d Proc. 35th International Conf. Machine Learning, pp.4075-4084, PMLR, 2018.","key":"27"},{"doi-asserted-by":"crossref","unstructured":"[29] E. Phaisangittisagul, \u201cAn analysis of the regularization between <i>L<\/i><sub>2<\/sub> and dropout in single hidden layer neural network,\u201d Proc. 2016 7th International Conf. Intelligent Systems, Modelling and Simulation, pp.174-179, IEEE, 2016. DOI: 10.1109\/ISMS.2016.14. 10.1109\/isms.2016.14","key":"28","DOI":"10.1109\/ISMS.2016.14"},{"unstructured":"[30] C. Sitaula and N. Ghimire, \u201cAn analysis of early stopping and dropout regularization in deep learning,\u201d International Journal of Conceptions on Computing and Information Technology, vol.5, no.1, pp.17-20, 2017.","key":"29"},{"unstructured":"[31] A. Lewkowycz and G. Gur-Ari, \u201cOn the training dynamics of deep networks with <i>L<\/i><sub>2<\/sub> regularization,\u201d Proc. Advances in Neural Information Processing Systems, 2020.","key":"30"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/8\/E108.D_2024EDP7235\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T03:29:24Z","timestamp":1754105364000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/8\/E108.D_2024EDP7235\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,1]]},"references-count":30,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edp7235","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2025,8,1]]},"article-number":"2024EDP7235"}}