170113 20260318155254.0 doi 10.1016/j.ins.2026.123275 sideral 148651 ART-2026-148651 eng Mayora-Cebollero, Carmen Universidad de Zaragoza (orcid)0000-0002-3431-0926 Bregman Proximal Gradient with extrapolation to train a Reservoir Computing network for a binary classification task 2026 This study examines the training process of Artificial Neural Networks, specifically focusing on Reservoir Computing and on binary classification tasks. Training involves optimizing the network’s parameters to minimize the error of a loss function, which quantifies the discrepancy between network outputs and target data. Several numerical optimizers are used in the literature. Here, we formulate the supervised learning problem using the recently introduced Bregman Proximal Gradient with extrapolation (BPGe) algorithm for non-convex optimization problems. We compare this new method with the classical Stochastic Gradient Descent (SGD), the Root Mean Square Propagation (RMSProp), the Adaptive Moment Estimation (Adam), and two variants with Nesterov momentum (NAG and NAdam). The new approach leads to an accurate and significantly faster numerical algorithm for solving supervised learning problems on binary classification tasks in Reservoir Computing. Three test examples are presented, one based on chaotic data classification in the classical Lorenz system, another on the Human Activity Recognition (HAR) using smartphones dataset for movement–rest classification, and the last one on the MNIST dataset for even–odd classification. We show that our approach is highly competitive with existing methods in the tests performed. Access copy available to the general public Unrestricted info:eu-repo/grantAgreement/ES/AEI/PID2021-122961NB-I00 info:eu-repo/grantAgreement/ES/DGA/E22-23R info:eu-repo/grantAgreement/ES/DGA/E24-23R info:eu-repo/grantAgreement/ES/DGA/LMP94_21 info:eu-repo/grantAgreement/ES/MCINN/PID2024-156032NB-I00 info:eu-repo/grantAgreement/ES/MICINN/PID2022-140556OB-I00 info:eu-repo/semantics/openAccess by-nc-nd https://creativecommons.org/licenses/by-nc-nd/4.0/deed.es info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Mayora-Cebollero, Ana Universidad de Zaragoza (orcid)0000-0002-4802-2511 Lozano, Álvaro Universidad de Zaragoza (orcid)0000-0002-1184-5901 Barrio, Roberto Universidad de Zaragoza (orcid)0000-0002-8089-343X 2006 440 Universidad de Zaragoza Dpto. Matemáticas Área Geometría y Topología 2005 595 Universidad de Zaragoza Dpto. Matemática Aplicada Área Matemática Aplicada 742 (2026), 123275 [25 pp.] Inf. sci. Information Sciences 0020-0255 5085764 http://zaguan.unizar.es/record/170113/files/texto_completo.pdf Versión publicada 1980386 http://zaguan.unizar.es/record/170113/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:170113 articulos driver 2026-03-18-13:52:34 ARTICLE