{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:48:18Z","timestamp":1770227298078,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004040","name":"KU Leuven","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9682842","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"5136-5143","source":"Crossref","is-referenced-by-count":3,"title":["Neural Network Training as an Optimal Control Problem : \u2014 An Augmented Lagrangian Approach \u2014"],"prefix":"10.1109","author":[{"given":"Brecht","family":"Evens","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puya","family":"Latafat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Themelis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan","family":"Suykens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panagiotis","family":"Patrinos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3362","article-title":"Fenchel lifted networks: A Lagrange relaxation of neural network training","author":"gu","year":"2020","journal-title":"Int Conf Arti Intel Stat"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"Gradient flow in recurrent nets: the di?culty of learning long-term dependencies","author":"hochreiter","year":"2001"},{"key":"ref13","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref14","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref15","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1991","journal-title":"Proc 4th Int Conf NIPS"},{"key":"ref16","author":"lecun","year":"1992","journal-title":"A Theoretical Framework for Back-Propagation"},{"key":"ref17","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"2013","journal-title":"Proc ICML"},{"key":"ref18","volume":"317","author":"rockafellar","year":"2009","journal-title":"Variational Analysis"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref4","first-page":"10","article-title":"Distributed optimization of deeply nested systems","author":"carreira-perpinan","year":"2014","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973365"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/18M1231559"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1391989.1391995"},{"key":"ref8","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Int Conf Mach Learn"},{"key":"ref7","volume":"ii","author":"facchinei","year":"2003","journal-title":"Finite-Dimensional Variational Inequalities and Complementarity Problems"},{"key":"ref2","author":"bertsekas","year":"2016","journal-title":"Nonlinear Programming"},{"key":"ref9","article-title":"On the complexity of an augmented La-grangian method for nonconvex optimization","author":"grapiglia","year":"2020","journal-title":"IMA J Numer Anal"},{"key":"ref1","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016"},{"key":"ref20","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"JMLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"ref21","first-page":"2722","article-title":"Training neural networks without gradients: A scalable ADMM approach","author":"taylor","year":"2016","journal-title":"Int Conf Mach Learn"},{"key":"ref24","first-page":"1719","article-title":"On the convergence of block coordinate descent in training dnns with Tikhonov regularization","author":"zhang","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330936"},{"key":"ref25","first-page":"1487","article-title":"E?cient training of very deep neural networks for supervised hashing","author":"zhang","year":"2016","journal-title":"Proc IEEE Conf Comput Vision Pattern Recogn"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","location":"Austin, TX, USA","start":{"date-parts":[[2021,12,14]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09682842.pdf?arnumber=9682842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:58:15Z","timestamp":1652201895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9682842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9682842","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}