{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T08:25:48Z","timestamp":1758702348101,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781094"},{"type":"electronic","value":"9783031781100"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78110-0_21","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:53:18Z","timestamp":1733089998000},"page":"322-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multiplicative RMSprop Using Gradient Normalization for\u00a0Learning Acceleration"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8670-0248","authenticated-orcid":false,"given":"Manos","family":"Kirtas","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1177-9139","authenticated-orcid":false,"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1288-3667","authenticated-orcid":false,"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"21_CR1","unstructured":"Brock, A., De, S., Smith, S.L., Simonyan, K.: High-performance large-scale image recognition without normalization (2021). https:\/\/arxiv.org\/abs\/2102.06171"},{"key":"21_CR2","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7) (2011)"},{"key":"21_CR3","unstructured":"Liu, L., et al.: On the variance of the adaptive learning rate and beyond (2019). https:\/\/arxiv.org\/abs\/1908.03265"},{"key":"21_CR4","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks (2017). https:\/\/arxiv.org\/abs\/1708.03888"},{"key":"21_CR5","unstructured":"Sun, S., Cao, Z., Zhu, H., Zhao, J.: A survey of optimization methods from a machine learning perspective (2019)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Arora, S., Hazan, E., Kale, S.: The multiplicative weights update method: a meta-algorithm and applications. Theory Comput. 8(6), 121\u2013164 (2012). https:\/\/theoryofcomputing.org\/articles\/v008a006","DOI":"10.4086\/toc.2012.v008a006"},{"issue":"4","key":"21_CR7","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/BF00116827","volume":"2","author":"N Littlestone","year":"1988","unstructured":"Littlestone, N.: Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm. Mach. Learn. 2(4), 285\u2013318 (1988)","journal-title":"Mach. Learn."},{"key":"21_CR8","unstructured":"Lee, D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: \u00a0Leen, T.,\u00a0Dietterich, T.,\u00a0Tresp, V. (eds.) Advances in Neural Information Processing Systems, vol.\u00a013. MIT Press (2000)"},{"issue":"6","key":"21_CR9","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1037\/h0042519","volume":"65","author":"F Rosenblatt","year":"1958","unstructured":"Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386 (1958)","journal-title":"Psychol. Rev."},{"key":"21_CR10","unstructured":"Bernstein, J., Vahdat, A., Yue, Y., Liu, M.Y.: On the distance between two neural networks and the stability of learning. In: Larochelle, H.,\u00a0Ranzato, M.,\u00a0Hadsell, R.,\u00a0Balcan, M.,\u00a0Lin, H. (eds.), vol.\u00a033. Curran Associates, Inc., 2020, pp. 21\u00a0370\u201321\u00a0381 (2020)"},{"key":"21_CR11","unstructured":"Bernstein, J., Zhao, J., Meister, M., Liu, M.Y., Anandkumar, A., Yue, Y.: Learning compositional functions via multiplicative weight updates. In: Larochelle, H.,\u00a0Ranzato, M.,\u00a0Hadsell, R.,\u00a0Balcan, M.,\u00a0Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033. Curran Associates, Inc., 2020, pp. 13\u00a0319\u201313\u00a0330"},{"key":"21_CR12","unstructured":"Bachlechner, T., Majumder, B.P., Mao, H., Cottrell, G., McAuley, J.: ReZero is all you need: fast convergence at large depth. In: 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021, no. UAI, pp. 1352\u20131361 (2021)"},{"key":"21_CR13","unstructured":"Zhang, J., He, T., Sra, S., Jadbabaie, A.: Why gradient clipping accelerates training: a theoretical justification for adaptivity (2019). https:\/\/arxiv.org\/abs\/1905.11881"},{"key":"21_CR14","unstructured":"Liu, L., et al.: On the variance of the adaptive learning rate and beyond (2019). https:\/\/arxiv.org\/abs\/1908.03265"},{"key":"21_CR15","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks (2017). https:\/\/arxiv.org\/abs\/1708.03888"},{"key":"21_CR16","first-page":"1","volume":"7","author":"M Kirtas","year":"2022","unstructured":"Kirtas, M., Passalis, N., Mourgias-Alexandris, G., Dabos, G., Pleros, N., Tefas, A.: Robust architecture-agnostic and noise resilient training of photonic deep learning models. IEEE Trans. Emerging Top. Comput. Intell. 7, 1\u201310 (2022)","journal-title":"IEEE Trans. Emerging Top. Comput. Intell."},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Passalis, N., Kirtas, M., Mourgias-Alexandris, G., Dabos, G., Pleros, N., Tefas, A.: Training noise-resilient recurrent photonic networks for financial time series analysis. In: 2020 28th European Signal Processing Conference (EUSIPCO), pp. 1556\u20131560 (2021)","DOI":"10.23919\/Eusipco47968.2020.9287649"},{"issue":"1","key":"21_CR18","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TNNLS.2014.2310059","volume":"26","author":"J Chorowski","year":"2015","unstructured":"Chorowski, J., Zurada, J.M.: Learning understandable neural networks with nonnegative weight constraints. IEEE Trans. Neural Netw. Learn. Syst. 26(1), 62\u201369 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Tsakyridis, A., et al.: Photonic neural networks and optics-informed deep learning fundamentals. APL Photonics 9(1), 011102 (2024). https:\/\/doi.org\/10.1063\/5.0169810","DOI":"10.1063\/5.0169810"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Pappas, C., et al.: A teraflop photonic matrix multiplier using time-space-wavelength multiplexed AWGR-based architectures. In: Optical Fiber Communications Conference and Exhibition (OFC)2024, pp. 1\u20133 (2024)","DOI":"10.1364\/OFC.2024.Th3G.1"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"21_CR22","unstructured":"Arora, S., Cohen, N., Hazan, E.: On the optimization of deep networks: implicit acceleration by overparameterization. In: Dy, J.\u00a0Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, vol.\u00a080. PMLR, 10\u201315 Jul 2018, pp. 244\u2013253 (2018). https:\/\/proceedings.mlr.press\/v80\/arora18a.html"},{"key":"21_CR23","unstructured":"Goodfellow, I.J., Vinyals, O., Saxe, A.M.: Qualitatively characterizing neural network optimization problems (2014). https:\/\/arxiv.org\/abs\/1412.6544"},{"key":"21_CR24","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"21_CR25","unstructured":"Abadi, M., Agarwal, A., et\u00a0al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/, software available from tensorflow.org"},{"issue":"12","key":"21_CR26","doi-asserted-by":"publisher","first-page":"2486","DOI":"10.1109\/TNNLS.2015.2479223","volume":"27","author":"E Hosseini-Asl","year":"2016","unstructured":"Hosseini-Asl, E., Zurada, J.M., Nasraoui, O.: Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints. IEEE Trans. Neural Netw. Learn. Syst. 27(12), 2486\u20132498 (2016)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR28","unstructured":"Simonyan, K.,\u00a0Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"21_CR29","unstructured":"Liu, Y., Bernstein, J., Meister, M., Yue, Y.: Learning by turning: neural architecture aware optimisation. In:\u00a0Meila, M.,\u00a0Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, vol. 139. PMLR, 18\u201324 Jul 2021, pp. 6748\u20136758 (2021)"},{"key":"21_CR30","unstructured":"You, Y., et al.: Large batch optimization for deep learning: training BERT in 76 minutes (2020)"},{"key":"21_CR31","unstructured":"Bernstein, J., Wang, Y.-X.,\u00a0Azizzadenesheli, K.,\u00a0Anandkumar, A.: signSGD: compressed optimisation for non-convex problems. In: International Conference on Machine Learning, pp. 560\u2013569. PMLR (2018)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78110-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:34:25Z","timestamp":1733096065000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78110-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031781094","9783031781100"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78110-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}