{"ID":2851009,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20254","arxiv_id":"2510.20254","title":"Anderson-type acceleration method for Deep Neural Network optimization","abstract":"In this paper we consider the neural network optimization. We develop Anderson-type acceleration method for the stochastic gradient decent method and it improves the network permanence very much. We demonstrate the applicability of the method for Deep Neural Network (DNN) and Convolution Neural Network (CNN).","short_abstract":"In this paper we consider the neural network optimization. We develop Anderson-type acceleration method for the stochastic gradient decent method and it improves the network permanence very much. We demonstrate the applicability of the method for Deep Neural Network (DNN) and Convolution Neural Network (CNN).","url_abs":"https://arxiv.org/abs/2510.20254","url_pdf":"https://arxiv.org/pdf/2510.20254v2","authors":"[\"Kazufumi Ito\",\"Tiancheng Xue\"]","published":"2025-10-23T06:23:21Z","proceeding":"math.NA","tasks":"[\"math.NA\",\"math.OC\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}