{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T09:46:48Z","timestamp":1770544008495,"version":"3.49.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727504","type":"print"},{"value":"9783031727511","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72751-1_19","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:52:13Z","timestamp":1729849933000},"page":"325-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Optimization Robustness in\u00a01-Bit Neural Networks Through Stochastic Sign Descent"],"prefix":"10.1007","author":[{"given":"Nianhui","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Meinel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haojin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Bai, H., et al.: BinaryBERT: Pushing the limit of BERT quantization. arXiv preprint arXiv:2012.15701 (2020)","DOI":"10.18653\/v1\/2021.acl-long.334"},{"key":"19_CR2","unstructured":"Balles, L., Hennig, P.: Dissecting ADAM: the sign, magnitude and variance of stochastic gradients. In: International Conference on Machine Learning, pp. 404\u2013413. PMLR (2018)"},{"key":"19_CR3","unstructured":"Bernstein, J., Wang, Y.X., Azizzadenesheli, K., Anandkumar, A.: signSGD: compressed optimisation for non-convex problems. In: International Conference on Machine Learning, pp. 560\u2013569. PMLR (2018)"},{"key":"19_CR4","unstructured":"Bernstein, J., Zhao, J., Azizzadenesheli, K., Anandkumar, A.: signSGD with majority vote is communication efficient and fault tolerant. arXiv preprint arXiv:1810.05291 (2018)"},{"key":"19_CR5","unstructured":"Bulat, A., Tzimiropoulos, G.: XNOR-Net++: Improved binary neural networks. arXiv preprint arXiv:1909.13863 (2019)"},{"key":"19_CR6","unstructured":"Chen, X., et\u00a0al.: Symbolic discovery of optimization algorithms. arXiv preprint arXiv:2302.06675 (2023)"},{"key":"19_CR7","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830 (2016)"},{"key":"19_CR8","unstructured":"Crawshaw, M., Liu, M., Orabona, F., Zhang, W., Zhuang, Z.: Robustness to unbounded smoothness of generalized signSGD. arXiv preprint arXiv:2208.11195 (2022)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"19_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"19_CR11","unstructured":"Guo, N., Bethge, J., Meinel, C., Yang, H.: Join the high accuracy club on ImageNet with a binary neural network ticket. arXiv preprint arXiv:2211.12933 (2022)"},{"key":"19_CR12","unstructured":"Guo, N., et al.: BoolNet: minimizing the energy consumption of binary neural networks. arXiv preprint arXiv:2106.06991 (2021)"},{"key":"19_CR13","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":"19_CR14","unstructured":"Helwegen, K., Widdicombe, J., Geiger, L., Liu, Z., Cheng, K.T., Nusselder, R.: Latent weights do not exist: Rethinking binarized neural network optimization. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"19_CR15","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 4114\u20134122 (2016)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: TinyBERT: Distilling BERT for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"19_CR17","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"19_CR18","unstructured":"Kunstner, F., Chen, J., Lavington, J.W., Schmidt, M.: Noise is not the main factor behind the gap between SGD and ADAM on transformers, but sign descent might be. arXiv preprint arXiv:2304.13960 (2023)"},{"key":"19_CR19","unstructured":"Liu, Z., et al.: BiT: Robustly binarized multi-distilled transformer. arXiv preprint arXiv:2205.13016 (2022)"},{"key":"19_CR20","unstructured":"Liu, Z., et al.: Official source code of bit on github (2022). https:\/\/github.com\/facebookresearch\/bit"},{"key":"19_CR21","unstructured":"Liu, Z., Shen, Z., Li, S., Helwegen, K., Huang, D., Cheng, K.T.: How Do Adam and Training Strategies Help BNNs Optimization? In: International Conference on Machine Learning, pp. 6936\u20136946. PMLR (2021), 2106.11309"},{"key":"19_CR22","unstructured":"Liu, Z., Shen, Z., Savvides, M., Cheng, K.: Official source code of ReActNET on Github (2020). https:\/\/github.com\/liuzechun\/ReActNet. Accessed 01 Oct 2021"},{"key":"19_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-030-58568-6_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Shen, Z., Savvides, M., Cheng, K.-T.: ReActNet: towards precise binary neural network with generalized activation functions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 143\u2013159. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_9"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.T.: Bi-Real Net: enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 722\u2013737 (2018)","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"19_CR25","unstructured":"Ma, S., et al.: The era of 1-bit LLMs: All large language models are in 1.58 bits. arXiv preprint arXiv:2402.17764 (2024)"},{"key":"19_CR26","unstructured":"Martinez, B., Yang, J., Bulat, A., Tzimiropoulos, G.: Training binary neural networks with real-to-binary convolutions. In: International Conference on Learning Representations (2020)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et\u00a0al.: Efficient large-scale language model training on GPU clusters using megatron-LM. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315 (2021)","DOI":"10.1145\/3458817.3476209"},{"key":"19_CR28","unstructured":"Qin, H., et al.: BiBERT: Accurate fully binarized BERT. arXiv preprint arXiv:2203.06390 (2022)"},{"key":"19_CR29","unstructured":"Qin, H., et al.: BiBERT: accurate fully binarized BERT. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Qin, H., et al.: Forward and backward information retention for accurate binary neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2250\u20132259 (2020)","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"19_CR31","unstructured":"Quist, J., Li, Y., van Gemert, J.: Understanding weight-magnitude hyperparameters in training binary networks. arXiv preprint arXiv:2303.02452 (2023)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: European Conference on Computer Vision, pp. 525\u2013542. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Shen, S., et al.: Q-BERT: hessian based ultra low precision quantization of BERT. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a034, pp. 8815\u20138821 (2020)","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"19_CR36","unstructured":"Wang, H., et al.: BitNet: Scaling 1-bit transformers for large language models. arXiv preprint arXiv:2310.11453 (2023)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: ReCU: reviving the dead weights in binary neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5198\u20135208 (2021)","DOI":"10.1109\/ICCV48922.2021.00515"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: TernaryBERT: Distillation-aware ultra-low bit BERT. arXiv preprint arXiv:2009.12812 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.37"},{"key":"19_CR39","unstructured":"Zhang, Y., et al.: Binarized neural machine translation. arXiv preprint arXiv:2302.04907 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72751-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T10:19:29Z","timestamp":1729851569000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72751-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031727504","9783031727511"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72751-1_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}