{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:44:09Z","timestamp":1743007449162,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030645793"},{"type":"electronic","value":"9783030645809"}],"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\/978-3-030-64580-9_5","type":"book-chapter","created":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T18:17:02Z","timestamp":1609957022000},"page":"39-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization"],"prefix":"10.1007","author":[{"given":"Mayumi","family":"Ohta","sequence":"first","affiliation":[]},{"given":"Nathaniel","family":"Berger","sequence":"additional","affiliation":[]},{"given":"Artem","family":"Sokolov","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Riezler","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,7]]},"reference":[{"key":"5_CR1","unstructured":"Agarwal, A., Dekel, O., Xiao, L.: Optimal algorithms for online convex optimization with multi-point bandit feedback. In: COLT (2010)"},{"key":"5_CR2","unstructured":"Balasubramanian, K., Ghadimi, S.: Zeroth-order nonconvex stochastic optimization: handling constraints, high-dimensionality and saddle-points. CoRR abs\/1809.06474 (2018)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chen, P.Y., Zhang, H., Sharma, Y., Yi, J., Hsieh, C.J.: Zoo: zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In: AISec (2017)","DOI":"10.1145\/3128572.3140448"},{"key":"5_CR4","unstructured":"Cheng, S., Dong, Y., Pang, T., Su, H., Zhu, J.: Improving black-box adversarial attacks with a transfer-based prior. In: NeurIPS (2019)"},{"issue":"5","key":"5_CR5","doi-asserted-by":"publisher","first-page":"2788","DOI":"10.1109\/TIT.2015.2409256","volume":"61","author":"JC Duchi","year":"2015","unstructured":"Duchi, J.C., Jordan, M.I., Wainwright, M.J., Wibisono, A.: Optimal rates for zero-order convex optimization: the power of two function evaluations. IEEE Trans. Inf. Theory 61(5), 2788\u20132806 (2015)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"5_CR6","unstructured":"Ebrahimi, S., Rohrbach, A., Darrell, T.: Gradient-free policy architecture search and adaptation. In: Proceedings of the Conference on Robot Learning (CoRL). Mountain View, CA, USA (2017)"},{"key":"5_CR7","unstructured":"Flaxman, A.D., Kalai, A.T., McMahan, H.B.: Online convex optimization in the bandit setting: gradient descent without a gradient. In: SODA (2005)"},{"key":"5_CR8","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: ICLR (2019)"},{"key":"5_CR9","unstructured":"Frankle, J., Dziugaite, G.K., Roy, D.M., Carbin, M.: Stabilizing the lottery ticket hypothesis. CoRR abs\/1903.01611 (2019)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Fu, M.C.: Gradient estimation. In: Henderson, S., Nelson, B. (eds.) Handbook in Operations Research and Management Science, vol. 13, pp. 575\u2013616. Elsevier (2006)","DOI":"10.1016\/S0927-0507(06)13019-4"},{"issue":"23","key":"5_CR11","first-page":"2342","volume":"4","author":"S Ghadimi","year":"2012","unstructured":"Ghadimi, S., Lan, G.: Stochastic first- and zeroth-order methods for nonconvex stochastic programming. SIAM J. Optim. 4(23), 2342\u20132368 (2012)","journal-title":"SIAM J. Optim."},{"key":"5_CR12","first-page":"249","volume":"9","author":"X Glorot","year":"2010","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. PMLR 9, 249\u2013256 (2010)","journal-title":"PMLR"},{"key":"5_CR13","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: NIPS (2015)"},{"key":"5_CR14","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, pp. 448\u2013456 (2015)"},{"key":"5_CR15","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: generalization gap and sharp minima. In: ICLR (2017)"},{"issue":"3","key":"5_CR16","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1214\/aoms\/1177729392","volume":"23","author":"J Kiefer","year":"1952","unstructured":"Kiefer, J., Wolfowitz, J.: Stochastic estimation of the maximum of a regression function. Ann. Math. Stat. 23(3), 462\u2013466 (1952)","journal-title":"Ann. Math. Stat."},{"key":"5_CR17","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Master\u2019s thesis, Department of Computer Science, University of Tront (2009)"},{"key":"5_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3223-4","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","author":"HJ Kushner","year":"2003","unstructured":"Kushner, H.J., Yin, G.G.: Stochastic Approximation and Recursive Algorithms and Applications, 2nd edn. Springer, Boston (2003). https:\/\/doi.org\/10.1007\/978-1-4614-3223-4","edition":"2"},{"issue":"11","key":"5_CR19","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(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Liu, S., Kailkhura, B., Chen, P.Y., Ting, P., Chang, S., Amini, L.: Zeroth-order stochastic variance reduction for nonconvex optimization. In: Advances in Neural Information Processing Systems 31. Montreal, Canada (2018)","DOI":"10.1109\/GlobalSIP.2018.8646618"},{"key":"5_CR21","unstructured":"Mania, H., Guy, A., Recht, B.: Simple random search provides a competitive approach to reinforcement learning. In: NIPS (2018)"},{"key":"5_CR22","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/s10208-015-9296-2","volume":"17","author":"Y Nesterov","year":"2015","unstructured":"Nesterov, Y., Spokoiny, V.: Random gradient-free minimization of convex functions. Found. Comput. Math. 17, 527\u2013566 (2015)","journal-title":"Found. Comput. Math."},{"key":"5_CR23","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. In: ICLR (2018)"},{"key":"5_CR24","unstructured":"Salimans, T., Ho, J., Chen, X., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. CoRR abs\/1703.03864 (2017)"},{"issue":"4","key":"5_CR25","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.neunet.2009.12.004","volume":"23","author":"F Sehnke","year":"2010","unstructured":"Sehnke, F., Osendorfer, C., R\u00fcckstie\u00df, T., Graves, A., Peters, J., Schmidhuber, J.: Parameter-exploring policy gradients. Neural Networks 23(4), 551\u2013559 (2010)","journal-title":"Neural Networks"},{"key":"5_CR26","first-page":"1","volume":"18","author":"O Shamir","year":"2017","unstructured":"Shamir, O.: An optimal algorithm for bandit and zero-order convex optimization with two-point feedback. JMLR 18, 1\u201311 (2017)","journal-title":"JMLR"},{"key":"5_CR27","unstructured":"Sokolov, A., Hitschler, J., Riezler, S.: Sparse stochastic zeroth-order optimization with an application to bandit structured prediction. CoRR abs\/1806.04458 (2018)"},{"issue":"3","key":"5_CR28","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1109\/9.119632","volume":"37","author":"JC Spall","year":"1992","unstructured":"Spall, J.C.: Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Trans. Autom. Control 37(3), 332\u2013341 (1992)","journal-title":"IEEE Trans. Autom. Control"},{"key":"5_CR29","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138","volume-title":"Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control","author":"JC Spall","year":"2003","unstructured":"Spall, J.C.: Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control. Wiley, Hoboken (2003)"},{"key":"5_CR30","unstructured":"Wang, Y., Du, S., Balakrishnan, S., Singh, A.: Stochastic zeroth-order optimization in high dimensions. In: AISTATS (2018)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Yue, Y., Joachims, T.: Interactively optimizing information retrieval systems as a dueling bandits problem. In: ICML (2009)","DOI":"10.1145\/1553374.1553527"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-64580-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T18:19:36Z","timestamp":1609957176000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-64580-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030645793","9783030645809"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-64580-9_5","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":"7 January 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Siena","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2020.icas.xyz\/","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":"in-house system and easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"209","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":"116","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":"56% - 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":"5-6","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":"1-2","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}