{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:54:16Z","timestamp":1783749256389,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"NWO","award":["OCENW.KLEIN.111"],"award-info":[{"award-number":["OCENW.KLEIN.111"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,15]]},"DOI":"10.1145\/3583131.3590368","type":"proceedings-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T19:40:19Z","timestamp":1689190819000},"page":"1127-1136","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Mini-Batching, Gradient-Clipping, First- versus Second-Order: What Works in Gradient-Based Coefficient Optimisation for Symbolic Regression?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3427-5251","authenticated-orcid":false,"given":"Joe","family":"Harrison","sequence":"first","affiliation":[{"name":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands"},{"name":"Delft University of Technology, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8905-9313","authenticated-orcid":false,"given":"Marco","family":"Virgolin","sequence":"additional","affiliation":[{"name":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4261-7511","authenticated-orcid":false,"given":"Tanja","family":"Alderliesten","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-6666","authenticated-orcid":false,"given":"Peter","family":"Bosman","sequence":"additional","affiliation":[{"name":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands"},{"name":"Delft University of Technology, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"US Congress.","year":"2022","unstructured":"117th US Congress. 2022 . Algorithmic accountability act. https:\/\/www.congress.gov\/bill\/117th-congress\/house-bill\/6580\/ 117th US Congress. 2022. Algorithmic accountability act. https:\/\/www.congress.gov\/bill\/117th-congress\/house-bill\/6580\/"},{"key":"e_1_3_2_2_2_1","unstructured":"Arthur Asuncion and David Newman. 2007. UCI machine learning repository.  Arthur Asuncion and David Newman. 2007. UCI machine learning repository."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.2166\/hydro.2000.0004"},{"key":"e_1_3_2_2_4_1","volume-title":"Exhaustive Symbolic Regression. arXiv preprint arXiv:2211.11461","author":"Bartlett Deaglan J","year":"2022","unstructured":"Deaglan J Bartlett , Harry Desmond , and Pedro G Ferreira . 2022. Exhaustive Symbolic Regression. arXiv preprint arXiv:2211.11461 ( 2022 ). Deaglan J Bartlett, Harry Desmond, and Pedro G Ferreira. 2022. Exhaustive Symbolic Regression. arXiv preprint arXiv:2211.11461 (2022)."},{"key":"e_1_3_2_2_5_1","volume-title":"International Conference on Machine Learning. PMLR, 936--945","author":"Biggio Luca","year":"2021","unstructured":"Luca Biggio , Tommaso Bendinelli , Alexander Neitz , Aurelien Lucchi , and Giambattista Parascandolo . 2021 . Neural symbolic regression that scales . In International Conference on Machine Learning. PMLR, 936--945 . Luca Biggio, Tommaso Bendinelli, Alexander Neitz, Aurelien Lucchi, and Giambattista Parascandolo. 2021. Neural symbolic regression that scales. In International Conference on Machine Learning. PMLR, 936--945."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377929.3398099"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2015.7257017"},{"key":"e_1_3_2_2_8_1","first-page":"17429","article-title":"Discovering symbolic models from deep learning with inductive biases","volume":"33","author":"Cranmer Miles","year":"2020","unstructured":"Miles Cranmer , Alvaro Sanchez Gonzalez , Peter Battaglia , Rui Xu , Kyle Cranmer , David Spergel , and Shirley Ho . 2020 . Discovering symbolic models from deep learning with inductive biases . Advances in Neural Information Processing Systems 33 (2020), 17429 -- 17442 . Miles Cranmer, Alvaro Sanchez Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, and Shirley Ho. 2020. Discovering symbolic models from deep learning with inductive biases. Advances in Neural Information Processing Systems 33 (2020), 17429--17442.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.02.040"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390237"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3322706.3361996"},{"key":"e_1_3_2_2_12_1","unstructured":"European Commission. 2021. Artificial intelligence act. https:\/\/artificialintelligenceact.eu\/  European Commission. 2021. Artificial intelligence act. https:\/\/artificialintelligenceact.eu\/"},{"key":"e_1_3_2_2_13_1","volume-title":"Genetic Programming 1998: Proceedings of the Third Annual Conference","author":"Evett Matthew","year":"1998","unstructured":"Matthew Evett and Thomas Fernandez . 1998. Numeric Mutation Improves the Discovery of Numeric Constants in Genetic Programming , Genetic Programming 1998: Proceedings of the Third Annual Conference , University of Wisconsin, Madison, Wisconsin, USA. University of Wisconsin , Madi-son, Wisconsin, USA ( 1998 ), 66--71. Matthew Evett and Thomas Fernandez. 1998. Numeric Mutation Improves the Discovery of Numeric Constants in Genetic Programming, Genetic Programming 1998: Proceedings of the Third Annual Conference, University of Wisconsin, Madison, Wisconsin, USA. University of Wisconsin, Madi-son, Wisconsin, USA (1998), 66--71."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio . 2010 . Understanding the difficulty of training deep feedforward neural networks . In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249--256 . Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249--256."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.09.007"},{"key":"e_1_3_2_2_17_1","volume-title":"International conference on machine learning. pmlr, 448--456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015 . Batch normalization: Accelerating deep network training by reducing internal covariate shift . In International conference on machine learning. pmlr, 448--456 . Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. pmlr, 448--456."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55696-3_3"},{"key":"e_1_3_2_2_19_1","volume-title":"Bayesian symbolic regression. arXiv preprint arXiv:1910.08892","author":"Jin Ying","year":"2019","unstructured":"Ying Jin , Weilin Fu , Jian Kang , Jiadong Guo , and Jian Guo . 2019. Bayesian symbolic regression. arXiv preprint arXiv:1910.08892 ( 2019 ). Ying Jin, Weilin Fu, Jian Kang, Jiadong Guo, and Jian Guo. 2019. Bayesian symbolic regression. arXiv preprint arXiv:1910.08892 (2019)."},{"key":"e_1_3_2_2_20_1","volume-title":"End-to-end symbolic regression with transformers. arXiv preprint arXiv:2204.10532","author":"Kamienny Pierre-Alexandre","year":"2022","unstructured":"Pierre-Alexandre Kamienny , St\u00e9phane d' Ascoli , Guillaume Lample , and Fran\u00e7ois Charton . 2022. End-to-end symbolic regression with transformers. arXiv preprint arXiv:2204.10532 ( 2022 ). Pierre-Alexandre Kamienny, St\u00e9phane d'Ascoli, Guillaume Lample, and Fran\u00e7ois Charton. 2022. End-to-end symbolic regression with transformers. arXiv preprint arXiv:2204.10532 (2022)."},{"key":"e_1_3_2_2_21_1","volume-title":"Symbolic regression by exhaustive search: reducing the search space using syntactical constraints and efficient semantic structure deduplication","author":"Kammerer Lukas","unstructured":"Lukas Kammerer , Gabriel Kronberger , Bogdan Burlacu , Stephan M Winkler , Michael Kommenda , and Michael Affenzeller . 2020. Symbolic regression by exhaustive search: reducing the search space using syntactical constraints and efficient semantic structure deduplication . In Genetic Programming Theory and Practice XVII. Springer , 79--99. Lukas Kammerer, Gabriel Kronberger, Bogdan Burlacu, Stephan M Winkler, Michael Kommenda, and Michael Affenzeller. 2020. Symbolic regression by exhaustive search: reducing the search space using syntactical constraints and efficient semantic structure deduplication. In Genetic Programming Theory and Practice XVII. Springer, 79--99."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36599-0_7"},{"key":"e_1_3_2_2_23_1","volume-title":"A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge. Scientific Reports 13","author":"Keren Liron Simon","year":"2023","unstructured":"Liron Simon Keren , Alex Liberzon , and Teddy Lazebnik . 2023. A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge. Scientific Reports 13 ( 2023 ). Issue 1. Liron Simon Keren, Alex Liberzon, and Teddy Lazebnik. 2023. A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge. Scientific Reports 13 (2023). Issue 1."},{"key":"e_1_3_2_2_24_1","volume-title":"On large-batch training for deep learning: Generalization gap and sharp minima. arXiv preprint arXiv:1609.04836","author":"Keskar Nitish Shirish","year":"2016","unstructured":"Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , and Ping Tak Peter Tang . 2016. On large-batch training for deep learning: Generalization gap and sharp minima. arXiv preprint arXiv:1609.04836 ( 2016 ). Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, and Ping Tak Peter Tang. 2016. On large-batch training for deep learning: Generalization gap and sharp minima. arXiv preprint arXiv:1609.04836 (2016)."},{"key":"e_1_3_2_2_25_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-019-09371-3"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464576.2482691"},{"key":"e_1_3_2_2_28_1","volume-title":"Genetic Programming: On the Programming of Computers by Means of Natural Selection.","author":"Koza John R","year":"1992","unstructured":"John R Koza . 1992 . Genetic Programming: On the Programming of Computers by Means of Natural Selection. Vol. 1 . MIT press Cambridge , MA , USA. John R Koza. 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection. Vol. 1. MIT press Cambridge, MA, USA."},{"key":"e_1_3_2_2_29_1","volume-title":"Local Optimization Often is Ill-conditioned in Genetic Programming for Symbolic Regression. arXiv preprint arXiv:2209.00942","author":"Kronberger Gabriel","year":"2022","unstructured":"Gabriel Kronberger . 2022. Local Optimization Often is Ill-conditioned in Genetic Programming for Symbolic Regression. arXiv preprint arXiv:2209.00942 ( 2022 ). Gabriel Kronberger. 2022. Local Optimization Often is Ill-conditioned in Genetic Programming for Symbolic Regression. arXiv preprint arXiv:2209.00942 (2022)."},{"key":"e_1_3_2_2_30_1","volume-title":"Marco Virgolin, Ying Jin, Michael Kommenda, and Jason H Moore.","author":"Cava William La","year":"2021","unstructured":"William La Cava , Patryk Orzechowski , Bogdan Burlacu , Fabr\u00edcio Olivetti de Fran\u00e7a , Marco Virgolin, Ying Jin, Michael Kommenda, and Jason H Moore. 2021 . Contemporary symbolic regression methods and their relative performance. arXiv preprint arXiv:2107.14351 (2021). William La Cava, Patryk Orzechowski, Bogdan Burlacu, Fabr\u00edcio Olivetti de Fran\u00e7a, Marco Virgolin, Ying Jin, Michael Kommenda, and Jason H Moore. 2021. Contemporary symbolic regression methods and their relative performance. arXiv preprint arXiv:2107.14351 (2021)."},{"key":"e_1_3_2_2_31_1","volume-title":"Deep learning for symbolic mathematics. arXiv preprint arXiv:1912.01412","author":"Lample Guillaume","year":"2019","unstructured":"Guillaume Lample and Fran\u00e7ois Charton . 2019. Deep learning for symbolic mathematics. arXiv preprint arXiv:1912.01412 ( 2019 ). Guillaume Lample and Fran\u00e7ois Charton. 2019. Deep learning for symbolic mathematics. arXiv preprint arXiv:1912.01412 (2019)."},{"key":"e_1_3_2_2_32_1","volume-title":"Petersen","author":"Landajuela Mikel","year":"2022","unstructured":"Mikel Landajuela , Chak Lee , Jiachen Yang , Ruben Glatt , Claudio P. Santiago , Ignacio Aravena , Terrell N. Mundhenk , Garrett Mulcahy , and Brenden K . Petersen . 2022 . A Unified Framework for Deep Symbolic Regression. In Advances in Neural Information Processing Systems, Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (Eds .). https:\/\/openreview.net\/forum?id=2FNnBhwJsHK Mikel Landajuela, Chak Lee, Jiachen Yang, Ruben Glatt, Claudio P. Santiago, Ignacio Aravena, Terrell N. Mundhenk, Garrett Mulcahy, and Brenden K. Petersen. 2022. A Unified Framework for Deep Symbolic Regression. In Advances in Neural Information Processing Systems, Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=2FNnBhwJsHK"},{"key":"e_1_3_2_2_33_1","volume-title":"A method for the solution of certain non-linear problems in least squares. Quarterly of applied mathematics 2, 2","author":"Levenberg Kenneth","year":"1944","unstructured":"Kenneth Levenberg . 1944. A method for the solution of certain non-linear problems in least squares. Quarterly of applied mathematics 2, 2 ( 1944 ), 164--168. Kenneth Levenberg. 1944. A method for the solution of certain non-linear problems in least squares. Quarterly of applied mathematics 2, 2 (1944), 164--168."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390213"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63710-1_19"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1137\/0111030"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of the 27th International Conference on International Conference on Machine Learning","author":"Nair Vinod","unstructured":"Vinod Nair and Geoffrey E. Hinton . 2010. Rectified Linear Units Improve Restricted Boltzmann Machines . In Proceedings of the 27th International Conference on International Conference on Machine Learning ( Haifa, Israel) (ICML'10). Omnipress, Madison, WI, USA, 807--814. Vinod Nair and Geoffrey E. Hinton. 2010. Rectified Linear Units Improve Restricted Boltzmann Machines. In Proceedings of the 27th International Conference on International Conference on Machine Learning (Haifa, Israel) (ICML'10). Omnipress, Madison, WI, USA, 807--814."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03991-2_52"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Michael O'Neill. 2009. Riccardo Poli William B. Langdon Nicholas F. McPhee: a field guide to genetic programming.  Michael O'Neill. 2009. Riccardo Poli William B. Langdon Nicholas F. McPhee: a field guide to genetic programming.","DOI":"10.1007\/s10710-008-9073-y"},{"key":"e_1_3_2_2_40_1","volume-title":"International conference on machine learning. PMLR, 1310--1318","author":"Pascanu Razvan","year":"2013","unstructured":"Razvan Pascanu , Tomas Mikolov , and Yoshua Bengio . 2013 . On the difficulty of training recurrent neural networks . In International conference on machine learning. PMLR, 1310--1318 . Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In International conference on machine learning. PMLR, 1310--1318."},{"key":"e_1_3_2_2_41_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_2_42_1","volume-title":"T Nathan Mundhenk, Claudio P Santiago, Soo K Kim, and Joanne T Kim.","author":"Petersen Brenden K","year":"2019","unstructured":"Brenden K Petersen , Mikel Landajuela Larma , T Nathan Mundhenk, Claudio P Santiago, Soo K Kim, and Joanne T Kim. 2019 . Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients. arXiv preprint arXiv:1912.04871 (2019). Brenden K Petersen, Mikel Landajuela Larma, T Nathan Mundhenk, Claudio P Santiago, Soo K Kim, and Joanne T Kim. 2019. Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients. arXiv preprint arXiv:1912.04871 (2019)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02056-8_2"},{"key":"e_1_3_2_2_44_1","volume-title":"An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747","author":"Ruder Sebastian","year":"2016","unstructured":"Sebastian Ruder . 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 ( 2016 ). Sebastian Ruder. 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)."},{"key":"e_1_3_2_2_45_1","volume-title":"Proceedings of the genetic and evolutionary computation conference (GECCO-2001)","volume":"155162","author":"Topchy Alexander","year":"2001","unstructured":"Alexander Topchy , William F Punch , 2001 . Faster genetic programming based on local gradient search of numeric leaf values . In Proceedings of the genetic and evolutionary computation conference (GECCO-2001) , Vol. 155162 . Morgan Kaufmann San Francisco, CA. Alexander Topchy, William F Punch, et al. 2001. Faster genetic programming based on local gradient search of numeric leaf values. In Proceedings of the genetic and evolutionary computation conference (GECCO-2001), Vol. 155162. Morgan Kaufmann San Francisco, CA."},{"key":"e_1_3_2_2_46_1","volume-title":"AI Feynman: A physics-inspired method for symbolic regression. Science Advances 6, 16","author":"Udrescu Silviu-Marian","year":"2020","unstructured":"Silviu-Marian Udrescu and Max Tegmark . 2020. AI Feynman: A physics-inspired method for symbolic regression. Science Advances 6, 16 ( 2020 ), eaay2631. Silviu-Marian Udrescu and Max Tegmark. 2020. AI Feynman: A physics-inspired method for symbolic regression. Science Advances 6, 16 (2020), eaay2631."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205604"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071287"},{"key":"e_1_3_2_2_49_1","volume-title":"Improving model-based genetic programming for symbolic regression of small expressions. Evolutionary computation 29, 2","author":"Virgolin Marco","year":"2021","unstructured":"Marco Virgolin , Tanja Alderliesten , Cees Witteveen , and Peter AN Bosman . 2021. Improving model-based genetic programming for symbolic regression of small expressions. Evolutionary computation 29, 2 ( 2021 ), 211--237. Marco Virgolin, Tanja Alderliesten, Cees Witteveen, and Peter AN Bosman. 2021. Improving model-based genetic programming for symbolic regression of small expressions. Evolutionary computation 29, 2 (2021), 211--237."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3534036"},{"key":"e_1_3_2_2_51_1","volume-title":"Symbolic Regression is NP-hard. arXiv preprint arXiv:2207.01018","author":"Virgolin Marco","year":"2022","unstructured":"Marco Virgolin and Solon P Pissis . 2022. Symbolic Regression is NP-hard. arXiv preprint arXiv:2207.01018 ( 2022 ). Marco Virgolin and Solon P Pissis. 2022. Symbolic Regression is NP-hard. arXiv preprint arXiv:2207.01018 (2022)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"e_1_3_2_2_53_1","volume-title":"Eliminating sharp minima from SGD with truncated heavy-tailed noise. arXiv preprint arXiv:2102.04297","author":"Wang Xingyu","year":"2021","unstructured":"Xingyu Wang , Sewoong Oh , and Chang-Han Rhee . 2021. Eliminating sharp minima from SGD with truncated heavy-tailed noise. arXiv preprint arXiv:2102.04297 ( 2021 ). Xingyu Wang, Sewoong Oh, and Chang-Han Rhee. 2021. Eliminating sharp minima from SGD with truncated heavy-tailed noise. arXiv preprint arXiv:2102.04297 (2021)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390180"},{"key":"e_1_3_2_2_55_1","first-page":"67","article-title":"Numerical optimization","volume":"35","author":"Wright Stephen","year":"1999","unstructured":"Stephen Wright , Jorge Nocedal , 1999 . Numerical optimization . Springer Science 35 , 67 -- 68 (1999), 7. Stephen Wright, Jorge Nocedal, et al. 1999. Numerical optimization. Springer Science 35, 67--68 (1999), 7.","journal-title":"Springer Science"},{"key":"e_1_3_2_2_56_1","unstructured":"Lei Wu Chao Ma etal 2018. How SGD selects the global minima in over-parameterized learning: A dynamical stability perspective. Advances in Neural Information Processing Systems 31 (2018).  Lei Wu Chao Ma et al. 2018. How SGD selects the global minima in over-parameterized learning: A dynamical stability perspective. Advances in Neural Information Processing Systems 31 (2018)."}],"event":{"name":"GECCO '23: Genetic and Evolutionary Computation Conference","location":"Lisbon Portugal","acronym":"GECCO '23","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583131.3590368","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583131.3590368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:49Z","timestamp":1750182529000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583131.3590368"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,12]]},"references-count":56,"alternative-id":["10.1145\/3583131.3590368","10.1145\/3583131"],"URL":"https:\/\/doi.org\/10.1145\/3583131.3590368","relation":{},"subject":[],"published":{"date-parts":[[2023,7,12]]},"assertion":[{"value":"2023-07-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}