Krzysztof C. Kiwiel, Convergence and efficiency of subgradient methods for quasiconvex minimization, in Mathematical Programming (Series A), vol. 90, n. 1, Berlin, Heidelberg, Springer, 2001, pp. 1–25, DOI:10.1007/PL00011414, ISSN 0025-5610 (WC · ACNP).
A Cichocki, T Chen e S Amari, Stability Analysis of Learning Algorithms for Blind Source Separation., in Neural networks : the official journal of the International Neural Network Society, vol. 10, n. 8, novembre 1997, pp. 1345–1351, PMID12662478.
Krzysztof C. Kiwiel, Convergence and efficiency of subgradient methods for quasiconvex minimization, in Mathematical Programming (Series A), vol. 90, n. 1, Berlin, Heidelberg, Springer, 2001, pp. 1–25, DOI:10.1007/PL00011414, ISSN 0025-5610 (WC · ACNP).
Ilya Sutskever, Martens, James, Dahl, George e Hinton, Geoffrey E., On the importance of initialization and momentum in deep learning (PDF), a cura di Sanjoy Dasgupta and David Mcallester, In Proceedings of the 30th international conference on machine learning (ICML-13), vol. 28, Atlanta, GA, giugno 2013, pp. 1139–1147. URL consultato il 14 gennaio 2016.
Joseph Perla, Notes on AdaGrad (PDF), su seed.ucsd.edu, 2014 (archiviato dall'url originale il 30 marzo 2015).
Maya R. Gupta, Samy Bengio e Jason Weston, Training highly multiclass classifiers (PDF), in JMLR, vol. 15, n. 1, 2014, pp. 1461–1492. URL consultato il 10 giugno 2018 (archiviato dall'url originale il 25 ottobre 2018).
Krzysztof C. Kiwiel, Convergence and efficiency of subgradient methods for quasiconvex minimization, in Mathematical Programming (Series A), vol. 90, n. 1, Berlin, Heidelberg, Springer, 2001, pp. 1–25, DOI:10.1007/PL00011414, ISSN 0025-5610 (WC · ACNP).