{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:44:18Z","timestamp":1743039858659,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030617912"},{"type":"electronic","value":"9783030617929"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-61792-9_32","type":"book-chapter","created":{"date-parts":[[2020,12,2]],"date-time":"2020-12-02T21:15:48Z","timestamp":1606943748000},"page":"401-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On Symmetry and Initialization for Neural Networks"],"prefix":"10.1007","author":[{"given":"Ido","family":"Nachum","sequence":"first","affiliation":[]},{"given":"Amir","family":"Yehudayoff","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,12,3]]},"reference":[{"key":"32_CR1","unstructured":"Abbe, E., Sandon, C.: Provable limitations of deep learning. arXiv e-prints p. 1812.06369 (2018)"},{"key":"32_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0168-0072(83)90038-6","volume":"24","author":"M Ajtai","year":"1983","unstructured":"Ajtai, M.: $$\\sum ^1_1$$-formulae on finite structures. Ann. Pure Appl. Logic 24, 1\u201348 (1983)","journal-title":"Ann. Pure Appl. Logic"},{"key":"32_CR3","unstructured":"Allen-Zhu, Z., Li, Y., Liang, Y.: Learning and generalization in overparameterized neural networks, going beyond two layers. arXiv e-prints p. 1811.04918 (2018)"},{"key":"32_CR4","unstructured":"Allen-Zhu, Z., Li, Y., Song, Z.: A convergence theory for deep learning via over-parameterization. arXiv e-prints p. 1811.03962 (2018)"},{"key":"32_CR5","unstructured":"Andoni, A., Panigrahy, R., Valiant, G., Zhang, L.: Learning polynomials with neural networks. In: Xing, E.P., Jebara, T. (eds.) Proceedings of the 31st International Conference on Machine Learning. pp. 1908\u20131916 (2014)"},{"key":"32_CR6","unstructured":"Arora, R., Basu, A., Mianjy, P., Mukherjee, A.: Understanding deep neural networks with rectified linear units. arXiv e-prints p. 1611.01491 (2016)"},{"key":"32_CR7","unstructured":"Arora, S., Du, S.S., Hu, W., Li, Z., Wang, R.: Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks. arXiv e-prints p. 1901.08584 (2019)"},{"key":"32_CR8","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1016\/S0925-2312(02)00610-0","volume":"48","author":"MZ Arslanov","year":"2002","unstructured":"Arslanov, M.Z., Ashigaliev, D.U., Ismail, E.: N-bit parity ordered neural networks. Neurocomput. 48, 1053\u20131056 (2002)","journal-title":"Neurocomput."},{"key":"32_CR9","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1515\/eng-2016-0037","volume":"6","author":"M Arslanov","year":"2016","unstructured":"Arslanov, M., Amirgalieva, Z.E., Kenshimov, C.A.: N-bit parity neural networks with minimum number of threshold neurons. Open Eng. 6, 309\u2013313 (2016)","journal-title":"Open Eng."},{"key":"32_CR10","unstructured":"Bartlett, P., Foster, D.J., Telgarsky, M.: Spectrally-normalized margin bounds for neural networks. arXiv e-prints p. 1706.08498 (2017)"},{"key":"32_CR11","unstructured":"Brutzkus, A., Globerson, A., Malach, E., Shalev-Shwartz, S.: SGD learns over-parameterized networks that provably generalize on linearly separable data. arXiv e-prints p. 1710.10174 (2018)"},{"key":"32_CR12","unstructured":"Chizat, L., Bach, F.: A note on lazy training in supervised differentiable programming. arXiv e-prints p. 1812.07956 (2018)"},{"key":"32_CR13","unstructured":"Cohen, T.S., Welling, M.: Group equivariant convolutional networks. arXiv e-prints p. 1602.07576 (2016)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Collobert, R., Bengio, S.: Links between perceptrons. In: Proceedings of the 21st International Conference on Machine Learning. p. 23 (2004)","DOI":"10.1145\/1015330.1015415"},{"key":"32_CR15","unstructured":"Daniely, A.: SGD learns the conjugate kernel class of the network. arXiv e-prints p. 1702.08503 (2017)"},{"key":"32_CR16","unstructured":"Du, S.S., Zhai, X., P\u00f3czos, B., Singh, A.: Gradient descent provably optimizes over-parameterized neural networks. arXiv e-prints p. 1810.02054 (2018)"},{"key":"32_CR17","unstructured":"Eldan, R., Shamir, O.: The power of depth for feedforward neural networks. In: Feldman, V., Rakhlin, A., Shamir, O. (eds.) Proceedings of the 29th Annual Conference on Learning Theory. Proceedings of Machine Learning Research, vol. 49, pp. 907\u2013940. PMLR, Columbia University, New York, USA (2016)"},{"key":"32_CR18","unstructured":"Elsayed, G.F., Krishnan, D., Mobahi, H., Regan, K., Bengio, S.: Large margin deep networks for classification. arXiv e-prints p. 1803.05598 (2018)"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Furst, M., Saxe, J.B., Sipser, M.: Parity, circuits, and the polynomial-time hierarchy. In: Proceedings of the 22nd Symposium on the Foundations of Computer Science. pp. 260\u2013270 (1981)","DOI":"10.1109\/SFCS.1981.35"},{"key":"32_CR20","unstructured":"Gens, R., Domingos, P.M.: Deep symmetry networks. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, NIPS 2014, pp. 2537\u20132545 (2014)"},{"key":"32_CR21","volume-title":"Computational Limitations of Small-depth Circuits","author":"J H\u00e5stad","year":"1987","unstructured":"H\u00e5stad, J.: Computational Limitations of Small-depth Circuits. MIT Press, United States (1987)"},{"key":"32_CR22","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1023\/B:NEPL.0000011147.74207.8c","volume":"18","author":"EM Iyoda","year":"2003","unstructured":"Iyoda, E.M., Nobuhara, H., Hirota, K.: A solution for the n-bit parity problem using a single translated multiplicative neuron. Neural Process. Lett. 18, 233\u2013238 (2003)","journal-title":"Neural Process. Lett."},{"key":"32_CR23","unstructured":"Jacot, A., Gabriel, F., Hongler, C.: Neural tangent kernel: Convergence and generalization in neural networks. arXiv e-prints p. arXiv:1806.07572 (2018)"},{"issue":"6","key":"32_CR24","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1145\/293347.293351","volume":"45","author":"M Kearns","year":"1998","unstructured":"Kearns, M.: Efficient noise-tolerant learning from statistical queries. J. ACM 45(6), 983\u20131006 (1998)","journal-title":"J. ACM"},{"key":"32_CR25","doi-asserted-by":"publisher","first-page":"L745","DOI":"10.1088\/0305-4470\/20\/11\/013","volume":"20","author":"W Krauth","year":"1987","unstructured":"Krauth, W., Mezard, M.: Learning algorithms with optimal stability in neural networks. J. Phys. A: Math. General 20, L745\u2013L752 (1987)","journal-title":"J. Phys. A: Math. General"},{"key":"32_CR26","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"32_CR27","unstructured":"Li, Y., Liang, Y.: Learning overparameterized neural networks via stochastic gradient descent on structured data. arXiv e-prints p. 1808.01204 (2018)"},{"key":"32_CR28","unstructured":"Littlestone, N., Warmuth, M.K.: Relating data compression and learnability (1986), Unpublished manuscript, University of California Santa Cruz (1986)"},{"key":"32_CR29","unstructured":"Liu, W., Wen, Y., Yu, Z., Yang, M.M.: Large-margin softmax loss for convolutional neural networks. arXiv e-prints p. 1612.02295 (2016)"},{"key":"32_CR30","volume-title":"Perceptrons","author":"ML Minsky","year":"1988","unstructured":"Minsky, M.L., Papert, S.A.: Perceptrons, Expanded edn. MIT Press, Cambridge, MA, USA (1988)","edition":"Expanded"},{"key":"32_CR31","unstructured":"Moran, S., Nachum, I., Panasoff, I., Yehudayoff, A.: On the perceptron\u2019s compression. arXiv e-prints p. 1806.05403 (2018)"},{"key":"32_CR32","first-page":"615","volume":"12","author":"ABJ Novikoff","year":"1962","unstructured":"Novikoff, A.B.J.: On convergence proofs on perceptrons. Proceedings of the Symposium on the Mathematical Theory of Automata. 12, 615\u2013622 (1962)","journal-title":"Proceedings of the Symposium on the Mathematical Theory of Automata."},{"key":"32_CR33","unstructured":"Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: Platt, J.C., Koller, D., Singer, Y., Roweis, S.T. (eds.) Advances in Neural Information Processing Systems 20, pp. 1177\u20131184 (2008)"},{"key":"32_CR34","unstructured":"Romero, E., Alquezar, R.: Maximizing the margin with feedforward neural networks. In: Proceedings of the 2002 International Joint Conference on Neural Networks, IJCNN 2002. vol. 1, pp. 743\u2013748 (2002)"},{"key":"32_CR35","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, 386\u2013408 (1958)","journal-title":"Psychol. Rev."},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Shalev-Shwartz, S., Ben-David, S.: Understanding machine learning: From theory to algorithms. Cambridge University Press (2014)","DOI":"10.1017\/CBO9781107298019"},{"key":"32_CR37","unstructured":"Shamir, O.: Distribution-specific hardness of learning neural networks. arXiv e-prints p. 1609.01037 (2016)"},{"key":"32_CR38","unstructured":"Sokolic, J., Giryes, R., Sapiro, G., Rodrigues, M.R.D.: Margin preservation of deep neural networks. arXiv e-prints p. 1605.08254v1 (2016)"},{"key":"32_CR39","doi-asserted-by":"publisher","first-page":"4265","DOI":"10.1109\/TSP.2017.2708039","volume":"65","author":"J Sokolic","year":"2017","unstructured":"Sokolic, J., Giryes, R., Sapiro, G., Rodrigues, M.R.D.: Robust large margin deep neural networks. IEEE Trans. Signal Process. 65, 4265\u20134280 (2017)","journal-title":"IEEE Trans. Signal Process."},{"key":"32_CR40","unstructured":"Song, L., Vempala, S., Wilmes, J., Xie, B.: On the complexity of learning neural networks. arXiv e-prints p. 1707.04615 (2017)"},{"key":"32_CR41","unstructured":"Soudry, D., Carmon, Y.: No bad local minima: Data independent training error guarantees for multilayer neural networks. arXiv e-prints p. 1605.08361 (2016)"},{"key":"32_CR42","unstructured":"Sun, S., Chen, W., Wang, L., Liu, T.Y.: Large margin deep neural networks: Theory and algorithms. arXiv e-prints p. 1506.05232 (2015)"},{"key":"32_CR43","unstructured":"Telgarsky, M.: Representation benefits of deep feedforward networks. arXiv e-prints p. 1509.08101 (2016)"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"Wilamowski, B., Hunter, D., Malinowski, A.: Solving parity-n problems with feedforward neural networks. In: Proceedings of the International Joint Conference on Neural Networks, IJCNN. vol. 4, pp. 2546\u20132551 (2003)","DOI":"10.1109\/IJCNN.2003.1223966"},{"key":"32_CR45","unstructured":"Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R., Smola, A.: Deep sets. In: Guyon, I., et al., (eds.) Advances in Neural Information Processing Systems 30, pp. 3391\u20133401 (2017)"},{"key":"32_CR46","unstructured":"Zou, D., Cao, Y., Zhou, D., Gu., Q.: Stochastic gradient descent optimizes over-parameterized deep relu networks. arXiv e-prints p. 1811.08888 (2018)"}],"container-title":["Lecture Notes in Computer Science","LATIN 2020: Theoretical Informatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61792-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T12:28:52Z","timestamp":1723984132000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-61792-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030617912","9783030617929"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61792-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LATIN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Latin American Symposium on Theoretical Informatics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sao Paulo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","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":"5 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"latin2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/latin2020.ime.usp.br\/","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":"136","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":"50","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":"37% - 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":"3,16","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic the symposium was moved from May 2020 to January 2021.","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)"}}]}}