{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T17:20:32Z","timestamp":1793035232548,"version":"4.5.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"11-12","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Hiroshi Fujiwara Technion Cyber Security Research Center","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s10994-021-06053-z","type":"journal-article","created":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T15:19:30Z","timestamp":1633101570000},"page":"3245-3262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":125,"title":["Loss aware post-training quantization"],"prefix":"10.1007","volume":"110","author":[{"given":"Yury","family":"Nahshan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Chmiel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaim","family":"Baskin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5400-9321","authenticated-orcid":false,"given":"Evgenii","family":"Zheltonozhskii","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ron","family":"Banner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex M.","family":"Bronstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avi","family":"Mendelson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,1]]},"reference":[{"key":"6053_CR1","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D. (2018) Post-training 4-bit quantization of convolution networks for rapid-deployment. arXiv preprint arXiv:181005723http:\/\/arxiv.org\/abs\/1810.05723"},{"key":"6053_CR2","unstructured":"Baskin, C., Liss, N., Chai, Y., Zheltonozhskii, E., Schwartz, E., Girayes, R., Mendelson, A., Bronstein, A. M. (2018) Nice: Noise injection and clamping estimation for neural network quantization. arXiv preprint arXiv:181000162http:\/\/arxiv.org\/abs\/1810.00162"},{"issue":"6","key":"6053_CR3","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1109\/TIT.1972.1054906","volume":"18","author":"T Berger","year":"1972","unstructured":"Berger, T. (1972). Optimum quantizers and permutation codes. IEEE Transactions on Information Theory, 18(6), 759\u2013765.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6053_CR4","unstructured":"Bethge, J., Yang, H., Bornstein, M., Meinel, C., (2019) Back to simplicity: How to train accurate bnns from scratch? arXiv preprint arXiv:190608637http:\/\/arxiv.org\/abs\/1906.08637"},{"key":"6053_CR5","unstructured":"Brent, R. P. (2013) Algorithms for minimization without derivatives. Courier Corporation."},{"key":"6053_CR6","doi-asserted-by":"crossref","unstructured":"Fang, J., Shafiee, A., Abdel-Aziz, H., Thorsley, D., Georgiadis, G., Hassoun, J. (2020) Near-lossless post-training quantization of deep neural networks via a piecewise linear approximation. arXiv preprint arXiv:200200104https:\/\/arxiv.org\/abs\/2002.00104","DOI":"10.1007\/978-3-030-58536-5_5"},{"key":"6053_CR7","doi-asserted-by":"crossref","unstructured":"Faraone, J., Fraser, N., Blott, M., Leong, P. H. (2018) Syq: Learning symmetric quantization for efficient deep neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/html\/Faraone_SYQ_Learning_Symmetric_CVPR_2018_paper.html","DOI":"10.1109\/CVPR.2018.00452"},{"key":"6053_CR8","unstructured":"Fawzi, A., Moosavi-Dezfooli, S. M., Frossard, P., (2016) Robustness of classifiers: from adversarial to random noise. arXiv preprint arXiv:160808967https:\/\/arxiv.org\/abs\/1608.08967"},{"key":"6053_CR9","unstructured":"Finkelstein, A., Almog, U., Grobman, M. (2019) Fighting quantization bias with bias. arXiv preprint arXiv:190603193http:\/\/arxiv.org\/abs\/1906.03193"},{"issue":"7","key":"6053_CR10","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1016\/j.cagd.2005.06.005","volume":"22","author":"R Goldman","year":"2005","unstructured":"Goldman, R. (2005). Curvature formulas for implicit curves and surfaces. Computer Aided Geometric Design, 22(7), 632\u2013658. https:\/\/doi.org\/10.1016\/j.cagd.2005.06.005.","journal-title":"Computer Aided Geometric Design"},{"key":"6053_CR11","doi-asserted-by":"crossref","unstructured":"Gong, J., Shen, H., Zhang, G., Liu, X., Li, S., Jin, G., Maheshwari, N., Fomenko, E., Segal, E. (2018) Highly efficient 8-bit low precision inference of convolutional neural networks with intelcaffe. In: Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning, ACM, New York, NY, USA, ReQuEST \u201918, 10.1145\/3229762.3229763, http:\/\/doi.acm.org\/10.1145\/3229762.3229763","DOI":"10.1145\/3229762.3229763"},{"key":"6053_CR12","doi-asserted-by":"crossref","unstructured":"Gong, R., Liu, X., Jiang, S., Li, T., Hu, P., Lin, J., Yu, F., Yan, J. (2019) Differentiable soft quantization: Bridging full-precision and low-bit neural networks. In: The IEEE International Conference on Computer Vision (ICCV), http:\/\/openaccess.thecvf.com\/content_ICCV_2019\/html\/Gong_Differentiable_Soft_Quantization_Bridging_Full-Precision_and_Low-Bit_Neural_Networks_ICCV_2019_paper.html","DOI":"10.1109\/ICCV.2019.00495"},{"key":"6053_CR13","doi-asserted-by":"crossref","unstructured":"He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T. S. (2017) Neural collaborative filtering. In: Proceedings of the 26th International Conference on World Wide Web, International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, WWW \u201917, pp 173\u2013182, 10.1145\/3038912.3052569, https:\/\/doi.org\/10.1145\/3038912.3052569","DOI":"10.1145\/3038912.3052569"},{"key":"6053_CR14","unstructured":"Hou, L., Kwok, J. T. (2018) Loss-aware weight quantization of deep networks. https:\/\/arxiv.org\/abs\/1802.08635"},{"key":"6053_CR15","unstructured":"Hou, L., Yao, Q., Kwok, J. T. (2016) Loss-aware binarization of deep networks. arXiv preprint arXiv:161101600https:\/\/arxiv.org\/abs\/1611.01600"},{"issue":"1","key":"6053_CR16","first-page":"6869","volume":"18","author":"I Hubara","year":"2017","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., & Bengio, Y. (2017). Quantized neural networks: Training neural networks with low precision weights and activations. J Mach Learn Res, 18(1), 6869\u20136898.","journal-title":"J Mach Learn Res"},{"key":"6053_CR17","unstructured":"Jin, Q., Yang, L., Liao, Z. (2019) Towards efficient training for neural network quantization. arXiv preprint arXiv:191210207https:\/\/arxiv.org\/abs\/1912.10207"},{"key":"6053_CR18","unstructured":"Kim, H., Kim, K., Kim, J., Kim, J. J. (2020) Binaryduo: Reducing gradient mismatch in binary activation network by coupling binary activations. arXiv preprint arXiv:200206517https:\/\/arxiv.org\/abs\/2002.06517"},{"key":"6053_CR19","unstructured":"Kravchik, E., Yang, F., Kisilev, P., Choukroun, Y. (2019) Low-bit quantization of neural networks for efficient inference. In: The IEEE International Conference on Computer Vision (ICCV) Workshops, http:\/\/openaccess.thecvf.com\/content_ICCVW_2019\/html\/CEFRL\/Kravchik_Low-bit_Quantization_of_Neural_Networks_for_Efficient_Inference_ICCVW_2019_paper.html"},{"key":"6053_CR20","unstructured":"Krishnamoorthi, R. (2018) Quantizing deep convolutional networks for efficient inference: A whitepaper. arXiv preprint arXiv:180608342http:\/\/arxiv.org\/abs\/1806.08342"},{"key":"6053_CR21","unstructured":"Lee, J. H., Ha, S., Choi, S., Lee, W.J., Lee, S. (2018) Quantization for rapid deployment of deep neural networks. arXiv preprint arXiv:181005488http:\/\/arxiv.org\/abs\/1810.05488"},{"key":"6053_CR22","unstructured":"Lin, D.D., Talathi, S.S., Annapureddy, V.S. (2015) Fixed point quantization of deep convolutional networks. arXiv preprint arXiv:151106393https:\/\/arxiv.org\/abs\/1511.06393"},{"key":"6053_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, W., Xia, X., Hu, Y., Zhang, B., Liu, J., Zhuang, B., Guo, G. (2019) Rectified binary convolutional networks for enhancing the performance of 1-bit DCNNs. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, International Joint Conferences on Artificial Intelligence Organization, pp 854\u2013860, 10.24963\/ijcai.2019\/120, https:\/\/doi.org\/10.24963\/ijcai.2019\/120","DOI":"10.24963\/ijcai.2019\/120"},{"issue":"2","key":"6053_CR24","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2), 129\u2013137.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"6053_CR25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TIT.1960.1057548","volume":"6","author":"J Max","year":"1960","unstructured":"Max, J. (1960). Quantizing for minimum distortion. IRE Transactions on Information Theory, 6(1), 7\u201312.","journal-title":"IRE Transactions on Information Theory"},{"key":"6053_CR26","unstructured":"Mellempudi, N., Kundu, A., Mudigere, D., Das, D., Kaul, B., Dubey, P. (2017) Ternary neural networks with fine-grained quantization. arXiv preprint arXiv:170501462http:\/\/arxiv.org\/abs\/1705.01462"},{"key":"6053_CR27","unstructured":"Migacz, S. (2017) 8-bit inference with tensorrt. http:\/\/on-demand.gputechconf.com\/gtc\/2017\/presentation\/s7310-8-bit-inference-with-tensorrt.pdf"},{"key":"6053_CR28","doi-asserted-by":"crossref","unstructured":"Nagel, M., Baalen, M.v., Blankevoort, T., Welling, M. (2019) Data-free quantization through weight equalization and bias correction. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1325\u20131334, http:\/\/openaccess.thecvf.com\/content_ICCV_2019\/html\/Nagel_Data-Free_Quantization_Through_Weight_Equalization_and_Bias_Correction_ICCV_2019_paper.html","DOI":"10.1109\/ICCV.2019.00141"},{"key":"6053_CR29","doi-asserted-by":"crossref","unstructured":"Nayak, P., Zhang, D., Chai, S. (2019) Bit efficient quantization for deep neural networks. arXiv preprint arXiv:191004877http:\/\/arxiv.org\/abs\/1910.04877","DOI":"10.1109\/EMC2-NIPS53020.2019.00020"},{"key":"6053_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.03.026","author":"H Peng","year":"2019","unstructured":"Peng, H., & Chen, S. (2019). Bdnn: Binary convolution neural networks for fast object detection. Pattern Recognition Letters. https:\/\/doi.org\/10.1016\/j.patrec.2019.03.026.","journal-title":"Pattern Recognition Letters"},{"issue":"2","key":"6053_CR31","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1093\/comjnl\/7.2.155","volume":"7","author":"MJ Powell","year":"1964","unstructured":"Powell, M. J. (1964). An efficient method for finding the minimum of a function of several variables without calculating derivatives. The Computer Journal, 7(2), 155.","journal-title":"The Computer Journal"},{"key":"6053_CR32","doi-asserted-by":"crossref","unstructured":"Yang, J., Shen, X., Xing, J., Tian, X., Li, H., Deng, B., Huang, J., Hua, X.s. (2019) Quantization networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), http:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Yang_Quantization_Networks_CVPR_2019_paper.html","DOI":"10.1109\/CVPR.2019.00748"},{"key":"6053_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yang, J., Ye, D., Hua, G. (2018) Lq-nets: Learned quantization for highly accurate and compact deep neural networks. In: The European Conference on Computer Vision (ECCV), http:\/\/openaccess.thecvf.com\/content_ECCV_2018\/html\/Dongqing_Zhang_Optimized_Quantization_for_ECCV_2018_paper.html","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"6053_CR34","unstructured":"Zhao, R., Hu, Y., Dotzel, J., De\u00a0Sa, C., Zhang, Z. (2019) Improving neural network quantization using outlier channel splitting. arXiv preprint arXiv:190109504https:\/\/arxiv.org\/abs\/1901.09504"},{"key":"6053_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Moosavi-Dezfooli, S.M., Cheung, N.M., Frossard, P. (2017) Adaptive quantization for deep neural network. arXiv preprint arXiv:171201048https:\/\/arxiv.org\/abs\/1712.01048","DOI":"10.1609\/aaai.v32i1.11623"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06053-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06053-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06053-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T02:08:08Z","timestamp":1664590088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06053-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,1]]},"references-count":35,"journal-issue":{"issue":"11-12","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["6053"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06053-z","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,1]]},"assertion":[{"value":"29 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}