{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:36:09Z","timestamp":1742913369968,"version":"3.40.3"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031159336"},{"type":"electronic","value":"9783031159343"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-15934-3_65","type":"book-chapter","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:02:53Z","timestamp":1662422573000},"page":"789-802","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Training 1-Bit Networks on\u00a0a\u00a0Sphere: A Geometric Approach"],"prefix":"10.1007","author":[{"given":"Luis","family":"Guerra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajanthan","family":"Thalaiyasingam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gil","family":"Avraham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Drummond","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,15]]},"reference":[{"key":"65_CR1","doi-asserted-by":"crossref","unstructured":"Ajanthan, T., Dokania, P.K., Hartley, R., Torr, P.H.: Proximal mean-field for neural network quantization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4871\u20134880 (2019)","DOI":"10.1109\/ICCV.2019.00497"},{"key":"65_CR2","unstructured":"Anderson, A.G., Berg, C.P.: The high-dimensional geometry of binary neural networks. arXiv preprint arXiv:1705.07199 (2017)"},{"key":"65_CR3","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"issue":"9","key":"65_CR4","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/TAC.2013.2254619","volume":"58","author":"S Bonnabel","year":"2013","unstructured":"Bonnabel, S.: Stochastic gradient descent on Riemannian manifolds. IEEE Trans. Autom. Control 58(9), 2217\u20132229 (2013)","journal-title":"IEEE Trans. Autom. Control"},{"key":"65_CR5","unstructured":"Boumal, N., Mishra, B., Absil, P.A., Sepulchre, R.: Manopt, a Matlab toolbox for optimization on manifolds. J. Mach. Learn. Res. 15(42), 1455\u20131459 (2014). https:\/\/www.manopt.org"},{"key":"65_CR6","doi-asserted-by":"crossref","unstructured":"Cai, Z., He, X., Sun, J., Vasconcelos, N.: Deep learning with low precision by half-wave gaussian quantization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5918\u20135926 (2017)","DOI":"10.1109\/CVPR.2017.574"},{"key":"65_CR7","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: BinaryConnect: training deep neural networks with binary weights during propagations. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 3123\u20133131 (2015)"},{"key":"65_CR8","unstructured":"Darabi, S., Belbahri, M., Courbariaux, M., Nia, V.P.: BNN+: improved binary network training. arXiv preprint arXiv:1812.11800 (2018)"},{"key":"65_CR9","unstructured":"Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1269\u20131277 (2014)"},{"key":"65_CR10","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wu, Y., Jia, Y., Harandi, M.: Learning to optimize on SPD manifolds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7700\u20137709 (2020)","DOI":"10.1109\/CVPR42600.2020.00772"},{"key":"65_CR11","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"key":"65_CR12","doi-asserted-by":"crossref","unstructured":"Gong, R., et al.: Differentiable soft quantization: bridging full-precision and low-bit neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4852\u20134861 (2019)","DOI":"10.1109\/ICCV.2019.00495"},{"key":"65_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"65_CR14","unstructured":"Guerra, L., Zhuang, B., Reid, I., Drummond, T.: Switchable precision neural networks. arXiv preprint arXiv:2002.02815 (2020)"},{"key":"65_CR15","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: Proceedings of the International Conference on Learning Representations (2016)"},{"key":"65_CR16","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, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"65_CR17","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":"65_CR18","doi-asserted-by":"crossref","unstructured":"He, Y., Liu, P., Wang, Z., Yang, Y.: Pruning filter via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00447"},{"key":"65_CR19","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"65_CR20","doi-asserted-by":"crossref","unstructured":"Hu, Q., Wang, P., Cheng, J.: From hashing to CNNs: training binary weight networks via hashing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11660"},{"key":"65_CR21","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 4107\u20134115 (2016)"},{"key":"65_CR22","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)"},{"key":"65_CR23","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. arXiv preprint arXiv:1405.3866 (2014)","DOI":"10.5244\/C.28.88"},{"key":"65_CR24","unstructured":"Kasai, H., Sato, H., Mishra, B.: Riemannian stochastic recursive gradient algorithm. In: International Conference on Machine Learning, pp. 2516\u20132524. PMLR (2018)"},{"key":"65_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"65_CR26","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"65_CR27","unstructured":"LeCun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Advances in Neural Information Processing Systems, pp. 598\u2013605 (1990)"},{"key":"65_CR28","unstructured":"Li, F., Zhang, B., Liu, B.: Ternary weight networks. arXiv preprint arXiv:1605.04711 (2016)"},{"key":"65_CR29","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: Proceedings of the International Conference on Learning Representations (2017)"},{"key":"65_CR30","unstructured":"Lin, M., et al.: Rotated binary neural network. arXiv preprint arXiv:2009.13055 (2020)"},{"key":"65_CR31","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: Proceedings of the International Conference on Learning Representations (2019)"},{"key":"65_CR32","unstructured":"Liu, W., et al.: Learning towards minimum hyperspherical energy. In: Advances in Neural Information Processing Systems, pp. 6222\u20136233 (2018)"},{"key":"65_CR33","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 (2018)","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"65_CR34","unstructured":"Louizos, C., Reisser, M., Blankevoort, T., Gavves, E., Welling, M.: Relaxed quantization for discretized neural networks. In: Proceedings of the International Conference on Learning Representations (2019)"},{"key":"65_CR35","unstructured":"Louizos, C., Welling, M., Kingma, D.P.: Learning sparse neural networks through $$ l_0 $$ regularization. In: Proceedings of the International Conference on Learning Representations (2018)"},{"key":"65_CR36","unstructured":"McDonnell, M.D.: Training wide residual networks for deployment using a single bit for each weight. arXiv preprint arXiv:1802.08530 (2018)"},{"key":"65_CR37","unstructured":"Mishkin, D., Matas, J.: All you need is a good init. arXiv preprint arXiv:1511.06422 (2015)"},{"key":"65_CR38","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"65_CR39","unstructured":"Pennington, J., Worah, P.: The spectrum of the fisher information matrix of a single-hidden-layer neural network. In: Advances in Neural Information Processing Systems, pp. 5410\u20135419 (2018)"},{"key":"65_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-46493-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Rastegari","year":"2016","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525\u2013542. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32"},{"key":"65_CR41","doi-asserted-by":"crossref","unstructured":"Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. arXiv preprint arXiv:1802.01548 (2018)","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"65_CR42","doi-asserted-by":"crossref","unstructured":"Roy, S.K., Mhammedi, Z., Harandi, M.: Geometry aware constrained optimization techniques for deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4460\u20134469 (2018)","DOI":"10.1109\/CVPR.2018.00469"},{"key":"65_CR43","unstructured":"Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: Advances in Neural Information Processing Systems, pp. 901\u2013909 (2016)"},{"issue":"2","key":"65_CR44","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1137\/17M1116787","volume":"29","author":"H Sato","year":"2019","unstructured":"Sato, H., Kasai, H., Mishra, B.: Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport. SIAM J. Optim. 29(2), 1444\u20131472 (2019)","journal-title":"SIAM J. Optim."},{"key":"65_CR45","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"65_CR46","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Quantization networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7308\u20137316 (2019)","DOI":"10.1109\/CVPR.2019.00748"},{"issue":"4","key":"65_CR47","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.1137\/18M1166134","volume":"11","author":"P Yin","year":"2018","unstructured":"Yin, P., Zhang, S., Lyu, J., Osher, S., Qi, Y., Xin, J.: BinaryRelax: a relaxation approach for training deep neural networks with quantized weights. SIAM J. Imaging Sci. 11(4), 2205\u20132223 (2018)","journal-title":"SIAM J. Imaging Sci."},{"key":"65_CR48","unstructured":"Yoshida, Y., Miyato, T.: Spectral norm regularization for improving the generalizability of deep learning. arXiv preprint arXiv:1705.10941 (2017)"},{"key":"65_CR49","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks (2016)","DOI":"10.5244\/C.30.87"},{"key":"65_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. arXiv preprint arXiv:1707.01083 (2017)","DOI":"10.1109\/CVPR.2018.00716"},{"issue":"10","key":"65_CR51","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1109\/TPAMI.2015.2502579","volume":"38","author":"X Zhang","year":"2016","unstructured":"Zhang, X., Zou, J., He, K., Sun, J.: Accelerating very deep convolutional networks for classification and detection. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 1943\u20131955 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"65_CR52","unstructured":"Zhuang, Z., et al.: Discrimination-aware channel pruning for deep neural networks. In: Proceedings of the Advances in Neural Information Processing Systems (2018)"},{"key":"65_CR53","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: Proceedings of the International Conference on Learning Representations (2017)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15934-3_65","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T06:07:05Z","timestamp":1663135625000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15934-3_65"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031159336","9783031159343"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15934-3_65","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"561","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"255","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}