{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:45:25Z","timestamp":1743075925161,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031255984"},{"type":"electronic","value":"9783031255991"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-25599-1_42","type":"book-chapter","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T04:32:27Z","timestamp":1678249947000},"page":"573-595","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Zeroth-Order Optimisation of\u00a0Nonconvex Composite Objectives"],"prefix":"10.1007","author":[{"given":"Weijia","family":"Shao","sequence":"first","affiliation":[]},{"given":"Sahin","family":"Albayrak","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,9]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Balasubramanian, K., Ghadimi, S.: Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points. Found. Comput. Math. 1\u201342 (2021)","DOI":"10.1007\/s10208-021-09499-8"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhou, D., Yi, J., Gu, Q.: A Frank-Wolfe framework for efficient and effective adversarial attacks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3486\u20133494 (2020)","DOI":"10.1609\/aaai.v34i04.5753"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Chen, P.Y., Sharma, Y., Zhang, H., Yi, J., Hsieh, C.J.: Ead: elastic-net attacks to deep neural networks via adversarial examples. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11302"},{"key":"42_CR4","unstructured":"Cutkosky, A., Boahen, K.: Online learning without prior information. In: Conference on Learning Theory, pp. 643\u2013677. PMLR (2017)"},{"key":"42_CR5","unstructured":"Cutkosky, A., Orabona, F.: Momentum-based variance reduction in non-convex SGD. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"42_CR6","unstructured":"Dhurandhar, A., et al.: Explanations based on the missing: towards contrastive explanations with pertinent negatives. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018)"},{"key":"42_CR7","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121\u20132159 (2011)"},{"issue":"5","key":"42_CR8","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"},{"issue":"3","key":"42_CR9","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1023\/A:1026319107706","volume":"53","author":"C Gentile","year":"2003","unstructured":"Gentile, C.: The robustness of the p-norm algorithms. Mach. Learn. 53(3), 265\u2013299 (2003)","journal-title":"Mach. Learn."},{"issue":"4","key":"42_CR10","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1137\/120880811","volume":"23","author":"S Ghadimi","year":"2013","unstructured":"Ghadimi, S., Lan, G.: Stochastic first-and zeroth-order methods for nonconvex stochastic programming. SIAM J. Optim. 23(4), 2341\u20132368 (2013)","journal-title":"SIAM J. Optim."},{"issue":"1\u20132","key":"42_CR11","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s10107-015-0871-8","volume":"156","author":"S Ghadimi","year":"2016","unstructured":"Ghadimi, S., Lan, G.: Accelerated gradient methods for nonconvex nonlinear and stochastic programming. Math. Program. 156(1\u20132), 59\u201399 (2016)","journal-title":"Math. Program."},{"issue":"1","key":"42_CR12","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s10107-014-0846-1","volume":"155","author":"S Ghadimi","year":"2016","unstructured":"Ghadimi, S., Lan, G., Zhang, H.: Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization. Math. Program. 155(1), 267\u2013305 (2016)","journal-title":"Math. Program."},{"key":"42_CR13","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"42_CR14","unstructured":"Huang, F., Tao, L., Chen, S.: Accelerated stochastic gradient-free and projection-free methods. In: International Conference on Machine Learning, pp. 4519\u20134530. PMLR (2020)"},{"issue":"6","key":"42_CR15","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1007\/s10444-017-9530-3","volume":"43","author":"R Iacono","year":"2017","unstructured":"Iacono, R., Boyd, J.P.: New approximations to the principal real-valued branch of the lambert w-function. Adv. Comput. Math. 43(6), 1403\u20131436 (2017)","journal-title":"Adv. Comput. Math."},{"key":"42_CR16","unstructured":"Jamieson, K.G., Nowak, R., Recht, B.: Query complexity of derivative-free optimization. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"42_CR17","unstructured":"Ji, K., Wang, Z., Zhou, Y., Liang, Y.: Improved zeroth-order variance reduced algorithms and analysis for nonconvex optimization. In: International Conference on Machine Learning, pp. 3100\u20133109. PMLR (2019)"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Kivinen, J., Warmuth, M.K.: Exponentiated gradient versus gradient descent for linear predictors. Inf. Comput. 132(1), 1\u201363 (1997)","DOI":"10.1006\/inco.1996.2612"},{"key":"42_CR19","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Master\u2019s thesis, University of Tront (2009)"},{"issue":"1\u20132","key":"42_CR20","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s10107-010-0434-y","volume":"133","author":"G Lan","year":"2012","unstructured":"Lan, G.: An optimal method for stochastic composite optimization. Math. Program. 133(1\u20132), 365\u2013397 (2012)","journal-title":"Math. Program."},{"key":"42_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-39568-1","volume-title":"First-Order and Stochastic Optimization Methods for Machine Learning","author":"G Lan","year":"2020","unstructured":"Lan, G.: First-Order and Stochastic Optimization Methods for Machine Learning. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-39568-1"},{"key":"42_CR22","unstructured":"Langford, J., Li, L., Zhang, T.: Sparse online learning via truncated gradient. J. Mach. Learn. Res. 10(3) (2009)"},{"key":"42_CR23","unstructured":"LeCun, Y., et al.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems, vol. 2 (1989)"},{"key":"42_CR24","unstructured":"Levy, Y.K., Yurtsever, A., Cevher, V.: Online adaptive methods, universality and acceleration. In: Advances in Neural Information Processing Systems, pp. 6500\u20136509 (2018)"},{"key":"42_CR25","unstructured":"Li, X., Orabona, F.: On the convergence of stochastic gradient descent with adaptive stepsizes. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 983\u2013992. PMLR (2019)"},{"key":"42_CR26","unstructured":"Lian, X., Zhang, H., Hsieh, C.J., Huang, Y., Liu, J.: A comprehensive linear speedup analysis for asynchronous stochastic parallel optimization from zeroth-order to first-order. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"42_CR27","unstructured":"Liu, S., Chen, J., Chen, P.Y., Hero, A.: Zeroth-order online alternating direction method of multipliers: convergence analysis and applications. In: International Conference on Artificial Intelligence and Statistics, pp. 288\u2013297. PMLR (2018)"},{"issue":"5","key":"42_CR28","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/MSP.2020.3003837","volume":"37","author":"S Liu","year":"2020","unstructured":"Liu, S., Chen, P.Y., Kailkhura, B., Zhang, G., Hero, A.O., III., Varshney, P.K.: A primer on zeroth-order optimization in signal processing and machine learning: principals, recent advances, and applications. IEEE Sig. Process. Mag. 37(5), 43\u201354 (2020)","journal-title":"IEEE Sig. Process. Mag."},{"key":"42_CR29","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, vol. 31 (2018)","DOI":"10.1109\/GlobalSIP.2018.8646618"},{"key":"42_CR30","unstructured":"Natesan Ramamurthy, K., Vinzamuri, B., Zhang, Y., Dhurandhar, A.: Model agnostic multilevel explanations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 5968\u20135979 (2020)"},{"key":"42_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course","author":"Y Nesterov","year":"2003","unstructured":"Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, New York (2003). https:\/\/doi.org\/10.1007\/978-1-4419-8853-9"},{"issue":"2","key":"42_CR32","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/s10208-015-9296-2","volume":"17","author":"Y Nesterov","year":"2017","unstructured":"Nesterov, Y., Spokoiny, V.: Random gradient-free minimization of convex functions. Found. Comput. Math. 17(2), 527\u2013566 (2017)","journal-title":"Found. Comput. Math."},{"key":"42_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/978-3-030-64580-9_5","volume-title":"Machine Learning, Optimization, and Data Science","author":"M Ohta","year":"2020","unstructured":"Ohta, M., Berger, N., Sokolov, A., Riezler, S.: Sparse perturbations for improved convergence in stochastic zeroth-order optimization. In: Nicosia, G., et al. (eds.) LOD 2020. LNCS, vol. 12566, pp. 39\u201364. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-64580-9_5"},{"key":"42_CR34","unstructured":"Orabona, F.: Dimension-free exponentiated gradient. In: NIPS, pp. 1806\u20131814 (2013)"},{"issue":"3","key":"42_CR35","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s10994-014-5474-8","volume":"99","author":"F Orabona","year":"2015","unstructured":"Orabona, F., Crammer, K., Cesa-Bianchi, N.: A generalized online mirror descent with applications to classification and regression. Mach. Learn. 99(3), 411\u2013435 (2015)","journal-title":"Mach. Learn."},{"issue":"110","key":"42_CR36","first-page":"1","volume":"21","author":"NH Pham","year":"2020","unstructured":"Pham, N.H., Nguyen, L.M., Phan, D.T., Tran-Dinh, Q.: Proxsarah: an efficient algorithmic framework for stochastic composite nonconvex optimization. J. Mach. Learn. Res. 21(110), 1\u201348 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"42_CR37","first-page":"1865","volume":"12","author":"S Shalev-Shwartz","year":"2011","unstructured":"Shalev-Shwartz, S., Tewari, A.: Stochastic methods for l 1-regularized loss minimization. J. Mach. Learn. Res. 12, 1865\u20131892 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"42_CR38","first-page":"1703","volume":"18","author":"O Shamir","year":"2017","unstructured":"Shamir, O.: An optimal algorithm for bandit and zero-order convex optimization with two-point feedback. J. Mach. Learn. Res. 18(1), 1703\u20131713 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"42_CR39","unstructured":"Wang, Y., Du, S., Balakrishnan, S., Singh, A.: Stochastic zeroth-order optimization in high dimensions. In: International Conference on Artificial Intelligence and Statistics, pp. 1356\u20131365. PMLR (2018)"},{"key":"42_CR40","doi-asserted-by":"crossref","unstructured":"Warmuth, M.K.: Winnowing subspaces. In: Proceedings of the 24th International Conference on Machine Learning, pp. 999\u20131006 (2007)","DOI":"10.1145\/1273496.1273622"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25599-1_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T17:17:45Z","timestamp":1680715065000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25599-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031255984","9783031255991"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25599-1_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 March 2023","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":"Certosa di Pontignano","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lod2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2022.icas.cc\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"226","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":"85","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":"38% - 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":"1.5","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)"}}]}}