{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:39:27Z","timestamp":1771702767379,"version":"3.50.1"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030926588","type":"print"},{"value":"9783030926595","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-92659-5_7","type":"book-chapter","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T07:09:18Z","timestamp":1642057758000},"page":"111-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Reintroducing Straight-Through Estimators as\u00a0Principled Methods for Stochastic Binary Networks"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Shekhovtsov","sequence":"first","affiliation":[]},{"given":"Viktor","family":"Yanush","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,13]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Ajanthan, T., Gupta, K., Torr, P.H., Hartley, R., Dokania, P.K.: Mirror descent view for neural network quantization. arXiv preprint arXiv:1910.08237 (2019)","DOI":"10.1109\/ICCV.2019.00497"},{"key":"7_CR2","unstructured":"Alizadeh, M., Fernandez-Marques, J., Lane, N.D., Gal, Y.: An empirical study of binary neural networks\u2019 optimisation. In: ICLR (2019)"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Azizan, N., Lale, S., Hassibi, B.: A study of generalization of stochastic mirror descent algorithms on overparameterized nonlinear models. In: ICASSP, pp. 3132\u20133136 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053864"},{"key":"7_CR4","unstructured":"Bai, Y., Wang, Y.-X., Liberty, E.: ProxQuant: quantized neural networks via proximal operators. In: ICLR (2019)"},{"key":"7_CR5","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"7_CR6","unstructured":"Bethge, J., Yang, H., Bornstein, M., Meinel, C.: Back to simplicity: how to train accurate BNNs from scratch? CoRR, abs\/1906.08637 (2019)"},{"issue":"123","key":"7_CR7","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/S0166-218X(01)00341-9","volume":"1\u20133","author":"E Boros","year":"2002","unstructured":"Boros, E., Hammer, P.: Pseudo-Boolean optimization. Discret. Appl. Math. 1\u20133(123), 155\u2013225 (2002)","journal-title":"Discret. Appl. Math."},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: Binarized convolutional landmark localizers for human pose estimation and face alignment with limited resources. In: ICCV, October 2017","DOI":"10.1109\/ICCV.2017.400"},{"key":"7_CR9","unstructured":"Bulat, A., Tzimiropoulos, G., Kossaifi, J., Pantic, M.: Improved training of binary networks for human pose estimation and image recognition. arXiv (2019)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Bulat, A., Martinez, B., Tzimiropoulos, G.: BATS: binary architecture search (2020)","DOI":"10.1007\/978-3-030-58592-1_19"},{"key":"7_CR11","unstructured":"Bulat, A., Martinez, B., Tzimiropoulos, G.: High-capacity expert binary networks. In: ICLR (2021)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Chaidaroon, S., Fang, Y.: Variational deep semantic hashing for text documents. In: SIGIR Conference on Research and Development in Information Retrieval, pp. 75\u201384 (2017)","DOI":"10.1145\/3077136.3080816"},{"key":"7_CR13","unstructured":"Cheng, P., Liu, C., Li, C., Shen, D., Henao, R., Carin, L.: Straight-through estimator as projected Wasserstein gradient flow. arXiv preprint arXiv:1910.02176 (2019)"},{"key":"7_CR14","unstructured":"Cong, Y., Zhao, M., Bai, K., Carin, L.: GO gradient for expectation-based objectives. In: ICLR (2019)"},{"key":"7_CR15","unstructured":"Courbariaux, M., Bengio, Y., David, J.-P.: BinaryConnect: training deep neural networks with binary weights during propagations. In: NeurIPS, pp. 3123\u20133131 (2015)"},{"key":"7_CR16","unstructured":"Dadaneh, S.Z., Boluki, S., Yin, M., Zhou, M., Qian, X.: Pairwise supervised hashing with Bernoulli variational auto-encoder and self-control gradient estimator. arXiv, abs\/2005.10477 (2020)"},{"key":"7_CR17","unstructured":"Dai, B., Guo, R., Kumar, S., He, N., Song, L.: Stochastic generative hashing. In: ICML 2017, pp. 913\u2013922 (2017)"},{"issue":"41","key":"7_CR18","doi-asserted-by":"publisher","first-page":"11441","DOI":"10.1073\/pnas.1604850113","volume":"113","author":"SK Esser","year":"2016","unstructured":"Esser, S.K., et al.: Convolutional networks for fast, energy-efficient neuromorphic computing. Proc. Natl. Acad. Sci. 113(41), 11441\u201311446 (2016)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"7_CR19","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\/CVF International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00495"},{"key":"7_CR20","unstructured":"Grathwohl, W., Choi, D., Wu, Y., Roeder, G., Duvenaud, D.: Backpropagation through the void: optimizing control variates for black-box gradient estimation. In: ICLR (2018)"},{"key":"7_CR21","unstructured":"Graves, A.: Practical variational inference for neural networks. In: NeurIPS, pp. 2348\u20132356 (2011)"},{"key":"7_CR22","unstructured":"Gregor, K., Danihelka, I., Mnih, A., Blundell, C., Wierstra, D.: Deep autoregressive networks. In: ICML (2014)"},{"key":"7_CR23","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: ICCV, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"7_CR24","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: NeurIPS, pp. 7531\u20137542 (2019)"},{"key":"7_CR25","unstructured":"Hinton, G.: Lecture 15D - Semantic hashing: 3:05\u20133:35 (2012). https:\/\/www.cs.toronto.edu\/~hinton\/coursera\/lecture15\/lec15d.mp4"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Horowitz, M.: Computing\u2019s energy problem (and what we can do about it). In: International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pp. 10\u201314 (2014)","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"7_CR27","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: NeurIPS, pp. 4107\u20134115 (2016)"},{"key":"7_CR28","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, vol. 37, pp. 448\u2013456 (2015)"},{"key":"7_CR29","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-Softmax. In: ICLR (2017)"},{"key":"7_CR30","unstructured":"Khan, E., Rue, H.: Learning algorithms from Bayesian principles. Draft v. 0.7, August 2020"},{"key":"7_CR31","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"7_CR32","unstructured":"Krizhevsky, A., Hinton, G.E.: Using very deep autoencoders for content-based image retrieval. In: ESANN (2011)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Lin, W., Khan, M.E., Schmidt, M.: Fast and simple natural-gradient variational inference with mixture of exponential-family approximations. In: ICML, vol. 97, June 2019","DOI":"10.23919\/ISITA.2018.8664326"},{"key":"7_CR34","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: ECCV, pp. 722\u2013737 (2018)","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Livochka, A., Shekhovtsov, A.: Initialization and transfer learning of stochastic binary networks from real-valued ones. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2021)","DOI":"10.1109\/CVPRW53098.2021.00524"},{"key":"7_CR36","unstructured":"Mart\u00ednez, B., Yang, J., Bulat, A., Tzimiropoulos, G.: Training binary neural networks with real-to-binary convolutions. In: ICLR (2020)"},{"key":"7_CR37","unstructured":"Meng, X., Bachmann, R., Khan, M.E.: Training binary neural networks using the Bayesian learning rule. In: ICML (2020)"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Nanculef, R., Mena, F.A., Macaluso, A., Lodi, S., Sartori, C.: Self-supervised Bernoulli autoencoders for semi-supervised hashing. CoRR, abs\/2007.08799 (2020)","DOI":"10.1007\/978-3-030-93420-0_25"},{"key":"7_CR39","unstructured":"Nemirovsky, A.S., Yudin, D.B.: Problem complexity and method efficiency in optimization (1983)"},{"key":"7_CR40","unstructured":"Owen, A.B.: Monte Carlo theory, methods and examples (2013)"},{"key":"7_CR41","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS, pp. 8024\u20138035 (2019)"},{"key":"7_CR42","unstructured":"Pervez, A., Cohen, T., Gavves, E.: Low bias low variance gradient estimates for Boolean stochastic networks. In: ICML, vol. 119, pp. 7632\u20137640, 13\u201318 July 2020"},{"key":"7_CR43","unstructured":"Peters, J.W., Welling, M.: Probabilistic binary neural networks. arXiv preprint arXiv:1809.03368 (2018)"},{"key":"7_CR44","unstructured":"Raiko, T., Berglund, M., Alain, G., Dinh, L.: Techniques for learning binary stochastic feedforward neural networks. In: ICLR (2015)"},{"key":"7_CR45","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":"7_CR46","doi-asserted-by":"crossref","unstructured":"Roth, W., Schindler, G., Fr\u00f6ning, H., Pernkopf, F.: Training discrete-valued neural networks with sign activations using weight distributions. In: European Conference on Machine Learning (ECML) (2019)","DOI":"10.1007\/978-3-030-46147-8_23"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Shekhovtsov, A.: Bias-variance tradeoffs in single-sample binary gradient estimators. In: GCPR (2021)","DOI":"10.1007\/978-3-030-92659-5_8"},{"key":"7_CR48","unstructured":"Shekhovtsov, A., Yanush, V., Flach, B.: Path sample-analytic gradient estimators for stochastic binary networks. In: NeurIPS (2020)"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Shen, D., et al.: NASH: toward end-to-end neural architecture for generative semantic hashing. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15\u201320 2018, Volume 1: Long Papers, pp. 2041\u20132050 (2018)","DOI":"10.18653\/v1\/P18-1190"},{"key":"7_CR50","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15, 1929\u20131958 (2014)","journal-title":"JMLR"},{"key":"7_CR51","unstructured":"Sun, Z., Yao, A.: Weights having stable signs are important: finding primary subnetworks and kernels to compress binary weight networks (2021)"},{"key":"7_CR52","doi-asserted-by":"crossref","unstructured":"Tang, W., Hua, G., Wang, L.: How to train a compact binary neural network with high accuracy? In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.10862"},{"key":"7_CR53","unstructured":"Titsias, M.K., L\u00e1zaro-Gredilla, M.: Local expectation gradients for black box variational inference. In: NeurIPS, pp. 2638\u20132646 (2015)"},{"key":"7_CR54","unstructured":"Tokui, S., Sato, I.: Evaluating the variance of likelihood-ratio gradient estimators. In: ICML, pp. 3414\u20133423 (2017)"},{"key":"7_CR55","unstructured":"Tucker, G., Mnih, A., Maddison, C.J., Lawson, J., Sohl-Dickstein, J.: REBAR: low-variance, unbiased gradient estimates for discrete latent variable models. In: NeurIPS (2017)"},{"key":"7_CR56","doi-asserted-by":"crossref","unstructured":"Xiang, X., Qian, Y., Yu, K.: Binary deep neural networks for speech recognition. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-1343"},{"key":"7_CR57","unstructured":"Yin, M., Zhou, M.: ARM: augment-REINFORCE-merge gradient for stochastic binary networks. In: ICLR (2019)"},{"key":"7_CR58","unstructured":"Yin, P., Lyu, J., Zhang, S., Osher, S., Qi, Y., Xin, J.: Understanding straight-through estimator in training activation quantized neural nets. arXiv preprint arXiv:1903.05662 (2019)"},{"key":"7_CR59","unstructured":"Zhang, S., He, N.: On the convergence rate of stochastic mirror descent for nonsmooth nonconvex optimization. arXiv, Optimization and Control (2018)"},{"key":"7_CR60","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92659-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T20:28:35Z","timestamp":1674419315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92659-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030926588","9783030926595"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92659-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"13 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bonn","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"116","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":"46","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":"0","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":"40% - 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":"2.95","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":"4.3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}