{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T16:28:05Z","timestamp":1782145685274,"version":"3.54.5"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,4,15]],"date-time":"2020-04-15T00:00:00Z","timestamp":1586908800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,4,15]],"date-time":"2020-04-15T00:00:00Z","timestamp":1586908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Math. Program."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s10107-020-01501-5","type":"journal-article","created":{"date-parts":[[2020,4,15]],"date-time":"2020-04-15T14:02:35Z","timestamp":1586959355000},"page":"19-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning"],"prefix":"10.1007","volume":"188","author":[{"given":"J\u00e9r\u00f4me","family":"Bolte","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edouard","family":"Pauwels","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,4,15]]},"reference":[{"key":"1501_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., Zheng, X.: Tensorflow: a system for large-scale machine learning. In: Symposium on Operating Systems Design and Implementation, OSDI, vol. 6, pp. 265\u2013283 (2016)"},{"key":"1501_CR2","unstructured":"Adil, S.: Op\u00e9rateurs monotones al\u00e9atoires et application \u00e0 l\u2019optimisation stochastique. PhD Thesis, Paris Saclay (2018)"},{"key":"1501_CR3","volume-title":"Infinite Dimensional Analysis","author":"CD Aliprantis","year":"2005","unstructured":"Aliprantis, C.D., Border, K.C.: Infinite Dimensional Analysis, 3rd edn. Springer, Berlin (2005)","edition":"3"},{"issue":"1","key":"1501_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1142\/S0219199700000025","volume":"2","author":"H Attouch","year":"2000","unstructured":"Attouch, H., Goudou, X., Redont, P.: The heavy ball with friction method, I. The continuous dynamical system: global exploration of the local minima of a real-valued function by asymptotic analysis of a dissipative dynamical system. Commun. Contemp. Math. 2(1), 1\u201334 (2000)","journal-title":"Commun. Contemp. Math."},{"key":"1501_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-69512-4","volume-title":"Differential Inclusions: Set-valued Maps and Viability Theory","author":"JP Aubin","year":"1984","unstructured":"Aubin, J.P., Cellina, A.: Differential Inclusions: Set-valued Maps and Viability Theory, vol. 264. Springer, Berlin (1984)"},{"key":"1501_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4848-0","volume-title":"Set-Valued Analysis","author":"J-P Aubin","year":"2009","unstructured":"Aubin, J.-P., Frankowska, H.: Set-Valued Analysis. Springer, Berlin (2009)"},{"key":"1501_CR7","unstructured":"Barakat, A., Bianchi, P.: Convergence and Dynamical Behavior of the Adam Algorithm for Non Convex Stochastic Optimization (2018). arXiv preprint arXiv:1810.02263"},{"issue":"1","key":"1501_CR8","first-page":"5595","volume":"18","author":"A Baydin","year":"2018","unstructured":"Baydin, A., Pearlmutter, B., Radul, A., Siskind, J.: Automatic differentiation in machine learning: a survey. J. Mach. Learn. Res. 18(1), 5595\u20135637 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"1501_CR9","doi-asserted-by":"crossref","unstructured":"Bena\u00efm, M.: Dynamics of stochastic approximation algorithms. In: S\u00e9minaire de Probabilit\u00e9s XXXIII, pp. 1\u201368. Springer, Berlin, Heidelberg (1999)","DOI":"10.1007\/BFb0096509"},{"issue":"1","key":"1501_CR10","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1137\/S0363012904439301","volume":"44","author":"M Bena\u00efm","year":"2005","unstructured":"Bena\u00efm, M., Hofbauer, J., Sorin, S.: Stochastic approximations and differential inclusions. SIAM J. Control Optim. 44(1), 328\u2013348 (2005)","journal-title":"SIAM J. Control Optim."},{"issue":"2","key":"1501_CR11","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1080\/17442508.2018.1539086","volume":"91","author":"P Bianchi","year":"2019","unstructured":"Bianchi, P., Hachem, W., Salim, A.: Constant step stochastic approximations involving differential inclusions: stability, long-run convergence and applications. Stochastics 91(2), 288\u2013320 (2019)","journal-title":"Stochastics"},{"issue":"2","key":"1501_CR12","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1137\/060670080","volume":"18","author":"J Bolte","year":"2007","unstructured":"Bolte, J., Daniilidis, A., Lewis, A., Shiota, M.: Clarke subgradients of stratifiable functions. SIAM J. Optim. 18(2), 556\u2013572 (2007)","journal-title":"SIAM J. Optim."},{"issue":"1\u20132","key":"1501_CR13","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/s10107-013-0701-9","volume":"146","author":"J Bolte","year":"2014","unstructured":"Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146(1\u20132), 459\u2013494 (2014)","journal-title":"Math. Program."},{"key":"1501_CR14","volume-title":"Stochastic Approximation: A Dynamical Systems Viewpoint","author":"V Borkar","year":"2009","unstructured":"Borkar, V.: Stochastic Approximation: A Dynamical Systems Viewpoint, vol. 48. Springer, Berlin (2009)"},{"key":"1501_CR15","volume-title":"Convex Analysis and Nonlinear Optimization: Theory and Examples","author":"J Borwein","year":"2010","unstructured":"Borwein, J., Lewis, A.S.: Convex Analysis and Nonlinear Optimization: Theory and Examples. Springer, Berlin (2010)"},{"issue":"2","key":"1501_CR16","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1006\/jfan.1997.3101","volume":"149","author":"JM Borwein","year":"1997","unstructured":"Borwein, J.M., Moors, W.B.: Essentially smooth Lipschitz functions. J. Funct. Anal. 149(2), 305\u2013351 (1997)","journal-title":"J. Funct. Anal."},{"issue":"2","key":"1501_CR17","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1137\/S1052623496297838","volume":"8","author":"JM Borwein","year":"1998","unstructured":"Borwein, J.M., Moors, W.B.: A chain rule for essentially smooth Lipschitz functions. SIAM J. Optim. 8(2), 300\u2013308 (1998)","journal-title":"SIAM J. Optim."},{"issue":"10","key":"1501_CR18","doi-asserted-by":"publisher","first-page":"3875","DOI":"10.1090\/S0002-9947-01-02820-3","volume":"353","author":"J Borwein","year":"2001","unstructured":"Borwein, J., Moors, W., Wang, X.: Generalized subdifferentials: a Baire categorical approach. Trans. Am. Math. Soc. 353(10), 3875\u20133893 (2001)","journal-title":"Trans. Am. Math. Soc."},{"key":"1501_CR19","unstructured":"Bottou, L., Bousquet, O.: The tradeoffs of large scale learning. In: Platt, J.C., Koller, D., Singer, Y., Roweis, S.T. (eds.) Advances in Neural Information Processing Systems, vol. 20, pp. 161\u2013168. Curran Associates, Inc. (2008)"},{"issue":"2","key":"1501_CR20","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"key":"1501_CR21","unstructured":"Castera, C., Bolte, J., F\u00e9votte, C., Pauwels, E.: An inertial Newton algorithm for deep learning (2019). arXiv preprint arXiv:1905.12278"},{"key":"1501_CR22","volume-title":"Optimization and Nonsmooth Analysis","author":"FH Clarke","year":"1983","unstructured":"Clarke, F.H.: Optimization and Nonsmooth Analysis. SIAM, Philadelphia (1983)"},{"key":"1501_CR23","unstructured":"Chizat, L., Bach F.: On the global convergence of gradient descent for over-parameterized models using optimal transport. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 3036\u20133046. Curran Associates, Inc. (2018)"},{"key":"1501_CR24","volume-title":"Automatic Differentiation Of Algorithms: From Simulation to Optimization","year":"2002","unstructured":"Corliss, G., Faure, C., Griewank, A., Hascoet, L., Naumann, U. (eds.): Automatic Differentiation Of Algorithms: From Simulation to Optimization. Springer, Berlin (2002)"},{"issue":"1","key":"1501_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BF00940840","volume":"61","author":"R Correa","year":"1989","unstructured":"Correa, R., Jofre, A.: Tangentially continuous directional derivatives in nonsmooth analysis. J. Optim. Theory Appl. 61(1), 1\u201321 (1989)","journal-title":"J. Optim. Theory Appl."},{"key":"1501_CR26","unstructured":"Coste, M.: An Introduction to O-Minimal Geometry. RAAG notes, Institut de Recherche Math\u00e9matique de Rennes, p. 81 (1999)"},{"issue":"1","key":"1501_CR27","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s10208-018-09409-5","volume":"20","author":"D Davis","year":"2020","unstructured":"Davis, D., Drusvyatskiy, D., Kakade, S., Lee, J.D.: Stochastic subgradient method converges on tame functions. Found. Comput. Math. 20(1), 119\u2013154 (2020)","journal-title":"Found. Comput. Math."},{"key":"1501_CR28","doi-asserted-by":"publisher","DOI":"10.1201\/b18333","volume-title":"Measure Theory and Fine Properties of Functions","author":"LC Evans","year":"2015","unstructured":"Evans, L.C., Gariepy, R.F.: Measure Theory and Fine Properties of Functions, Revised edn. Chapman and Hall\/CRC, London (2015)","edition":"Revised"},{"key":"1501_CR29","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315\u2013323 (2011)"},{"key":"1501_CR30","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717761","volume-title":"Evaluating Derivatives: Principles and Techniques of Algorithmic Differentiation","author":"A Griewank","year":"2008","unstructured":"Griewank, A., Walther, A.: Evaluating Derivatives: Principles and Techniques of Algorithmic Differentiation, vol. 105. SIAM, Philadelphia (2008)"},{"issue":"6","key":"1501_CR31","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1080\/10556788.2013.796683","volume":"28","author":"A Griewank","year":"2013","unstructured":"Griewank, A.: On stable piecewise linearization and generalized algorithmic differentiation. Optim. Methods Softw. 28(6), 1139\u20131178 (2013)","journal-title":"Optim. Methods Softw."},{"issue":"1\u20132","key":"1501_CR32","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s10107-015-0934-x","volume":"158","author":"A Griewank","year":"2016","unstructured":"Griewank, A., Walther, A., Fiege, S., Bosse, T.: On Lipschitz optimization based on gray-box piecewise linearization. Math. Program. 158(1\u20132), 383\u2013415 (2016)","journal-title":"Math. Program."},{"issue":"1","key":"1501_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1090\/S0002-9947-1981-0613784-7","volume":"266","author":"AD Ioffe","year":"1981","unstructured":"Ioffe, A.D.: Nonsmooth analysis: differential calculus of nondifferentiable mappings. Trans. Am. Math. Soc. 266(1), 1\u201356 (1981)","journal-title":"Trans. Am. Math. Soc."},{"key":"1501_CR34","series-title":"Springer Monographs in Mathematics","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64277-2","volume-title":"Variational Analysis of Regular Mappings","author":"AD Ioffe","year":"2017","unstructured":"Ioffe, A.D.: Variational Analysis of Regular Mappings. Springer Monographs in Mathematics. Springer, Cham (2017)"},{"key":"1501_CR35","unstructured":"Kakade, S.M., Lee, J.D.: Provably correct automatic sub-differentiation for qualifed programs. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp 7125\u20137135. Curran Associates, Inc. (2018)"},{"issue":"3","key":"1501_CR36","doi-asserted-by":"publisher","first-page":"769","DOI":"10.5802\/aif.1638","volume":"48","author":"K Kurdyka","year":"1998","unstructured":"Kurdyka, K.: On gradients of functions definable in o-minimal structures. Ann. l\u2019inst. Fourier 48(3), 769\u2013783 (1998)","journal-title":"Ann. l\u2019inst. Fourier"},{"issue":"3","key":"1501_CR37","doi-asserted-by":"publisher","first-page":"763","DOI":"10.2307\/2661354","volume":"152","author":"K Kurdyka","year":"2000","unstructured":"Kurdyka, K., Mostowski, T., Parusinski, A.: Proof of the gradient conjecture of R. Thom. Ann. Math. 152(3), 763\u2013792 (2000)","journal-title":"Ann. Math."},{"key":"1501_CR38","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","author":"H Kushner","year":"2003","unstructured":"Kushner, H., Yin, G.G.: Stochastic Approximation and Recursive Algorithms and Applications, vol. 35. Springer, Berlin (2003)"},{"issue":"7553","key":"1501_CR39","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Le Cun","year":"2015","unstructured":"Le Cun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"issue":"4","key":"1501_CR40","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1109\/TAC.1977.1101561","volume":"22","author":"L Ljung","year":"1977","unstructured":"Ljung, L.: Analysis of recursive stochastic algorithms. IEEE Trans. Autom. Control 22(4), 551\u2013575 (1977)","journal-title":"IEEE Trans. Autom. Control"},{"key":"1501_CR41","unstructured":"Majewski, S., Miasojedow, B., Moulines, E.: Analysis of nonsmooth stochastic approximation: the differential inclusion approach (2018). arXiv preprint arXiv:1805.01916"},{"key":"1501_CR42","volume-title":"Applied Shape Optimization for Fluids","author":"B Mohammadi","year":"2010","unstructured":"Mohammadi, B., Pironneau, O.: Applied Shape Optimization for Fluids. Oxford University Press, Oxford (2010)"},{"key":"1501_CR43","unstructured":"Moulines, E., Bach, F.R.: Non-asymptotic analysis of stochastic approximation algorithms for machine learning. In Shawe-Taylor, J., Zemel, R.S., Bartlett, P.L., Pereira, F., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 24, pp. 451\u2013459. Curran Associates, Inc. (2011)"},{"key":"1501_CR44","unstructured":"Moreau J.-J.: Fonctionnelles sous-diff\u00e9rentiables, S\u00e9minaire Jean Leray (1963)"},{"key":"1501_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31246-3","volume-title":"Variational Analysis and Generalized Differentiation\u00a0i: Basic Theory","author":"BS Mordukhovich","year":"2006","unstructured":"Mordukhovich, B.S.: Variational Analysis and Generalized Differentiation\u00a0i: Basic Theory. Springer, Berlin (2006)"},{"key":"1501_CR46","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in Pytorch. In: NIPS Workshops (2017)"},{"key":"1501_CR47","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"1501_CR48","unstructured":"Rockafellar, R.T.: Convex functions and dual extremum problems. Doctoral dissertation, Harvard University (1963)"},{"issue":"1","key":"1501_CR49","doi-asserted-by":"publisher","first-page":"209","DOI":"10.2140\/pjm.1970.33.209","volume":"33","author":"R Rockafellar","year":"1970","unstructured":"Rockafellar, R.: On the maximal monotonicity of subdifferential mappings. Pacific J. Math. 33(1), 209\u2013216 (1970)","journal-title":"Pacific J. Math."},{"key":"1501_CR50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02431-3","volume-title":"Variational Analysis","author":"RT Rockafellar","year":"1998","unstructured":"Rockafellar, R.T., Wets, R.J.B.: Variational Analysis. Springer, Berlin (1998)"},{"key":"1501_CR51","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"E Rumelhart","year":"1986","unstructured":"Rumelhart, E., Hinton, E., Williams, J.: Learning representations by back-propagating errors. Nature 323, 533\u2013536 (1986)","journal-title":"Nature"},{"key":"1501_CR52","doi-asserted-by":"crossref","unstructured":"Speelpenning, B.: Compiling fast partial derivatives of functions given by algorithms (No. COO-2383-0063; UILU-ENG-80-1702; UIUCDCS-R-80-1002). Illinois Univ., Urbana (USA). Dept. of Computer Science (1980)","DOI":"10.2172\/5254402"},{"issue":"1","key":"1501_CR53","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1006\/jmaa.1995.1003","volume":"189","author":"L Thibault","year":"1995","unstructured":"Thibault, L., Zagrodny, D.: Integration of subdifferentials of lower semicontinuous functions on Banach spaces. J. Math. Anal. Appl. 189(1), 33\u201358 (1995)","journal-title":"J. Math. Anal. Appl."},{"key":"1501_CR54","doi-asserted-by":"crossref","unstructured":"Thibault, L., Zlateva, N.: Integrability of subdifferentials of directionally Lipschitz functions. In: Proceedings of the American Mathematical Society, pp. 2939\u20132948 (2005)","DOI":"10.1090\/S0002-9939-05-07883-4"},{"key":"1501_CR55","first-page":"241","volume":"308","author":"M Valadier","year":"1989","unstructured":"Valadier, M.: Entra\u00eenement unilat\u00e9ral, lignes de descente, fonctions lipschitziennes non pathologiques. C. R. l\u2019Acad. Sci. 308, 241\u2013244 (1989)","journal-title":"C. R. l\u2019Acad. Sci."},{"issue":"2","key":"1501_CR56","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1215\/S0012-7094-96-08416-1","volume":"84","author":"L van den Dries","year":"1996","unstructured":"van den Dries, L., Miller, C.: Geometric categories and o-minimal structures. Duke Math. J 84(2), 497\u2013540 (1996)","journal-title":"Duke Math. J"},{"key":"1501_CR57","unstructured":"Wang, X.: Pathological Lipschitz functions in $${\\mathbb{R}}^n$$. Master thesis, Simon Fraser University (1995)"}],"container-title":["Mathematical Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10107-020-01501-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10107-020-01501-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10107-020-01501-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T10:31:41Z","timestamp":1666348301000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10107-020-01501-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,15]]},"references-count":57,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["1501"],"URL":"https:\/\/doi.org\/10.1007\/s10107-020-01501-5","relation":{},"ISSN":["0025-5610","1436-4646"],"issn-type":[{"value":"0025-5610","type":"print"},{"value":"1436-4646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,15]]},"assertion":[{"value":"5 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}