{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:58:14Z","timestamp":1742921894605,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730030"},{"type":"electronic","value":"9783031730047"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73004-7_3","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:02:14Z","timestamp":1730394134000},"page":"36-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalizable Symbolic Optimizer Learning"],"prefix":"10.1007","author":[{"given":"Xiaotian","family":"Song","sequence":"first","affiliation":[]},{"given":"Peng","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Yanan","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Andy","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"3_CR1","unstructured":"Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"3_CR2","unstructured":"Bello, I., Zoph, B., Vasudevan, V., Le, Q.V.: Neural optimizer search with reinforcement learning. In: International Conference on Machine Learning, pp. 459\u2013468 (2017)"},{"key":"3_CR3","unstructured":"Bentivogli, L., Clark, P., Dagan, I., Giampiccolo, D.: The fifth PASCAL recognizing textual entailment challenge. In: TAC, vol. 7, no. 8 (2009)"},{"key":"3_CR4","unstructured":"Carmon, Y., Raghunathan, A., Schmidt, L., Duchi, J.C., Liang, P.S.: Unlabeled data improves adversarial robustness. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Cauligi, A., Culbertson, P., Stellato, B., Bertsimas, D., Schwager, M., Pavone, M.: Learning mixed-integer convex optimization strategies for robot planning and control. In: 2020 59th IEEE Conference on Decision and Control (CDC), pp. 1698\u20131705 (2020)","DOI":"10.1109\/CDC42340.2020.9304043"},{"issue":"1","key":"3_CR6","first-page":"8562","volume":"23","author":"T Chen","year":"2022","unstructured":"Chen, T., et al.: Learning to optimize: a primer and a benchmark. J. Mach. Learn. Res. 23(1), 8562\u20138620 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR7","unstructured":"Chen, X., et\u00a0al.: Symbolic discovery of optimization algorithms. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3_CR8","unstructured":"Croce, F., et al.: RobustBench: a standardized adversarial robustness benchmark. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2021). https:\/\/openreview.net\/forum?id=SSKZPJCt7B"},{"key":"3_CR9","unstructured":"Croce, F., Hein, M.: Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: International Conference on Machine Learning, pp. 2206\u20132216 (2020)"},{"key":"3_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"3_CR11","unstructured":"Dolan, B., Brockett, C.: Automatically constructing a corpus of sentential paraphrases. In: Third International Workshop on Paraphrasing (IWP2005) (2005)"},{"issue":"7","key":"3_CR12","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7), 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Engstrom, L., Ilyas, A., Salman, H., Santurkar, S., Tsipras, D.: Robustness (python library) 4(4), 4\u20133 (2019). https:\/\/github.com\/MadryLab\/robustness","DOI":"10.23915\/distill.00019.7"},{"issue":"6","key":"3_CR14","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1109\/TRPMS.2021.3066428","volume":"5","author":"FL Fan","year":"2021","unstructured":"Fan, F.L., Xiong, J., Li, M., Wang, G.: On interpretability of artificial neural networks: a survey. IEEE Trans. Radiat. Plasma Med. Sci. 5(6), 741\u2013760 (2021). https:\/\/doi.org\/10.1109\/TRPMS.2021.3066428","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Giles, C.L., Bollacker, K.D., Lawrence, S.: Citeseer: an automatic citation indexing system. In: Proceedings of the Third ACM Conference on Digital Libraries, pp. 89\u201398 (1998)","DOI":"10.1145\/276675.276685"},{"key":"3_CR16","unstructured":"Gowal, S., Qin, C., Uesato, J., Mann, T., Kohli, P.: Uncovering the limits of adversarial training against norm-bounded adversarial examples. arXiv preprint arXiv:2010.03593 (2020)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"3_CR18","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"3_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"3_CR20","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: Handbook of Systemic Autoimmune Diseases, vol. 1, no. 4 (2009)"},{"key":"3_CR21","unstructured":"Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019 (2015)"},{"key":"3_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"3_CR23","unstructured":"Lv, K., Jiang, S., Li, J.: Learning gradient descent: better generalization and longer horizons. In: International Conference on Machine Learning, pp. 2247\u20132255 (2017)"},{"key":"3_CR24","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"3_CR25","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1023\/A:1009953814988","volume":"3","author":"AK McCallum","year":"2000","unstructured":"McCallum, A.K., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retrieval 3, 127\u2013163 (2000)","journal-title":"Inf. Retrieval"},{"key":"3_CR26","unstructured":"Metz, L., et\u00a0al.: VeLO: training versatile learned optimizers by scaling up. arXiv preprint arXiv:2211.09760 (2022)"},{"key":"3_CR27","unstructured":"Metz, L., Maheswaranathan, N., Nixon, J., Freeman, D., Sohl-Dickstein, J.: Understanding and correcting pathologies in the training of learned optimizers. In: International Conference on Machine Learning, pp. 4556\u20134565 (2019)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Orchard, J., Wang, L.: The evolution of a generalized neural learning rule. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 4688\u20134694 (2016)","DOI":"10.1109\/IJCNN.2016.7727815"},{"key":"3_CR29","unstructured":"Real, E., Liang, C., So, D., Le, Q.: AutoML-Zero: evolving machine learning algorithms from scratch. In: International Conference on Machine Learning, pp. 8007\u20138019 (2020)"},{"issue":"3","key":"3_CR30","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22(3), 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"3_CR31","unstructured":"Sahoo, S., Lampert, C., Martius, G.: Learning equations for extrapolation and control. In: International Conference on Machine Learning, pp. 4442\u20134450 (2018)"},{"key":"3_CR32","unstructured":"Sehwag, V., Wang, S., Mittal, P., Jana, S.: HYDRA: pruning adversarially robust neural networks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 19655\u201319666 (2020)"},{"issue":"3","key":"3_CR33","first-page":"93","volume":"29","author":"P Sen","year":"2008","unstructured":"Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93 (2008)","journal-title":"AI Mag."},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631\u20131642 (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"3_CR35","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-RMSProp, COURSERA: neural networks for machine learning. Technical report 6, University of Toronto (2012)"},{"issue":"2","key":"3_CR36","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1137\/S1052623495294797","volume":"8","author":"P Tseng","year":"1998","unstructured":"Tseng, P.: An incremental gradient (-projection) method with momentum term and adaptive stepsize rule. SIAM J. Optim. 8(2), 506\u2013531 (1998)","journal-title":"SIAM J. Optim."},{"key":"3_CR37","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"3_CR39","unstructured":"Wang, R., Xiong, Y., Cheng, M., Hsieh, C.J.: Efficient non-parametric optimizer search for diverse tasks. In: Advances in Neural Information Processing Systems (2022)"},{"key":"3_CR40","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1162\/tacl_a_00290","volume":"7","author":"A Warstadt","year":"2019","unstructured":"Warstadt, A., Singh, A., Bowman, S.R.: Neural network acceptability judgments. Trans. Assoc. Comput. Linguist. 7, 625\u2013641 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"3_CR41","unstructured":"Wichrowska, O., et al.: Learned optimizers that scale and generalize. In: International Conference on Machine Learning, pp. 3751\u20133760 (2017)"},{"key":"3_CR42","unstructured":"Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: revisiting adversarial training. arXiv preprint arXiv:2001.03994 (2020)"},{"key":"3_CR43","unstructured":"Wu, D., Xia, S.T., Wang, Y.: Adversarial weight perturbation helps robust generalization. In: Advances in Neural Information Processing Systems, vol. 33, pp. 2958\u20132969 (2020)"},{"key":"3_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-3-030-58598-3_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Xiong","year":"2020","unstructured":"Xiong, Y., Hsieh, C.-J.: Improved adversarial training via learned optimizer. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part VIII. LNCS, vol. 12353, pp. 85\u2013100. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_6"},{"key":"3_CR45","unstructured":"Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.I., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. In: Proceedings of the 35th International Conference on Machine Learning, vol.\u00a080, pp. 5453\u20135462 (2018)"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)","DOI":"10.5244\/C.30.87"},{"key":"3_CR47","unstructured":"Zheng, W., Chen, T., Hu, T.K., Wang, Z.: Symbolic learning to optimize: towards interpretability and scalability. In: International Conference on Learning Representations (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73004-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T16:16:09Z","timestamp":1732983369000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}