{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T09:52:51Z","timestamp":1782208371806,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"AISG","award":["AISG3-RP-2022-031"],"award-info":[{"award-number":["AISG3-RP-2022-031"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,24]]},"DOI":"10.1145\/3806789.3810252","type":"proceedings-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T09:31:40Z","timestamp":1782207100000},"page":"78-87","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dimensional Peeking for Low-Variance Gradients in Zeroth-Order Discrete Optimization via Simulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0211-7136","authenticated-orcid":false,"given":"Philipp","family":"Andelfinger","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0782-1341","authenticated-orcid":false,"given":"Wentong","family":"Cai","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Kingma DP Ba\u00a0J Adam et\u00a0al. 2014. A method for stochastic optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1412.6980 1412 6 (2014)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Philipp Andelfinger. 2023. Towards differentiable agent-based simulation. ACM Transactions on Modeling and Computer Simulation 32 4 (2023) 1\u201326.","DOI":"10.1145\/3565810"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3726301.3728410"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63775-9_16"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Gaurav Arya Moritz Schauer Frank Sch\u00e4fer and Christopher Rackauckas. 2022. Automatic differentiation of programs with discrete randomness. Advances in Neural Information Processing Systems 35 (2022) 10435\u201310447.","DOI":"10.52202\/068431-0758"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2330784.2330919"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Krishnakumar Balasubramanian and Saeed Ghadimi. 2022. Zeroth-order nonconvex stochastic optimization: Handling constraints high dimensionality and saddle points. Foundations of Computational Mathematics 22 1 (2022) 35\u201376.","DOI":"10.1007\/s10208-021-09499-8"},{"key":"e_1_3_3_2_9_2","volume-title":"Second Agent Learning in Open-Endedness Workshop","author":"Chopra Ayush","year":"2023","unstructured":"Ayush Chopra, Jayakumar Subramanian, Balaji Krishnamurthy, and Ramesh Raskar. 2023. Agenttorch: Agent-based modeling with automatic differentiation. In Second Agent Learning in Open-Endedness Workshop."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"David\u00a0J Eckman Shane\u00a0G Henderson and Sara Shashaani. 2023. SimOpt: A testbed for simulation-optimization experiments. INFORMS Journal on Computing 35 2 (2023) 495\u2013508.","DOI":"10.1287\/ijoc.2023.1273"},{"key":"e_1_3_3_2_11_2","unstructured":"Cong Fang Chris\u00a0Junchi Li Zhouchen Lin and Tong Zhang. 2018. Spider: Near-optimal non-convex optimization via stochastic path-integrated differential estimator. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Yasong Feng and Tianyu Wang. 2023. Stochastic zeroth-order gradient and Hessian estimators: variance reduction and refined bias bounds. Information and Inference: A Journal of the IMA 12 3 (2023) 1514\u20131545.","DOI":"10.1093\/imaiai\/iaad014"},{"key":"e_1_3_3_2_13_2","unstructured":"Michael\u00a0C Fu. 2006. Gradient estimation. Handbooks in operations research and management science 13 (2006) 575\u2013616."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-1384-8"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Saeed Ghadimi and Guanghui Lan. 2013. Stochastic first-and zeroth-order methods for nonconvex stochastic programming. SIAM Journal on Optimization 23 4 (2013) 2341\u20132368.","DOI":"10.1137\/120880811"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Wei-Bo Gong and Yu-Chi Ho. 1987. Smoothed (conditional) perturbation analysis of discrete event dynamical systems. IEEE Trans. Automat. Control 32 10 (1987) 858\u2013866.","DOI":"10.1109\/TAC.1987.1104464"},{"key":"e_1_3_3_2_17_2","first-page":"3100","volume-title":"International conference on machine learning","author":"Ji Kaiyi","year":"2019","unstructured":"Kaiyi Ji, Zhe Wang, Yi Zhou, and Yingbin Liang. 2019. Improved zeroth-order variance reduced algorithms and analysis for nonconvex optimization. In International conference on machine learning. PMLR, 3100\u20133109."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"David Kozak Cesare Molinari Lorenzo Rosasco Luis Tenorio and Silvia Villa. 2023. Zeroth-order optimization with orthogonal random directions. Mathematical Programming 199 1 (2023) 1179\u20131219.","DOI":"10.1007\/s10107-022-01866-9"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Justin\u00a0N Kreikemeyer and Philipp Andelfinger. 2023. Smoothing methods for automatic differentiation across conditional branches. IEEE Access (2023).","DOI":"10.1109\/ACCESS.2023.3342136"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Jeffrey Larson Matt Menickelly and Stefan\u00a0M Wild. 2019. Derivative-free optimization methods. Acta Numerica 28 (2019) 287\u2013404.","DOI":"10.1017\/S0962492919000060"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Chih-Jen Lin and Jorge\u00a0J Mor\u00e9. 1999. Newton\u2019s method for large bound-constrained optimization problems. SIAM Journal on Optimization 9 4 (1999) 1100\u20131127.","DOI":"10.1137\/S1052623498345075"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Charles\u00a0C Margossian. 2019. A review of automatic differentiation and its efficient implementation. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 9 4 (2019) e1305.","DOI":"10.1002\/widm.1305"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Lester\u00a0James Miranda. 2018. PySwarms: a research toolkit for Particle Swarm Optimization in Python. Journal of Open Source Software 3 21 (2018) 433.","DOI":"10.21105\/joss.00433"},{"key":"e_1_3_3_2_24_2","first-page":"7805","volume-title":"International Conference on Machine Learning","author":"Mora Miguel Angel\u00a0Zamora","year":"2021","unstructured":"Miguel Angel\u00a0Zamora Mora, Momchil Peychev, Sehoon Ha, Martin Vechev, and Stelian Coros. 2021. Pods: Policy optimization via differentiable simulation. In International Conference on Machine Learning. PMLR, 7805\u20137817."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Yurii Nesterov and Vladimir Spokoiny. 2017. Random gradient-free minimization of convex functions. Foundations of Computational Mathematics 17 2 (2017) 527\u2013566.","DOI":"10.1007\/s10208-015-9296-2"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Rhys Newbury Jack Collins Kerry He Jiahe Pan Ingmar Posner David Howard and Akansel Cosgun. 2024. A review of differentiable simulators. IEEE Access (2024).","DOI":"10.1109\/ACCESS.2024.3425448"},{"key":"e_1_3_3_2_27_2","unstructured":"Felix Petersen Christian Borgelt Aashwin Mishra and Stefano Ermon. 2024. Generalizing stochastic smoothing for differentiation and gradient estimation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.08125 (2024)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68713-7"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Roman Poya Antonio\u00a0J Gil and Rogelio Ortigosa. 2017. A high performance data parallel tensor contraction framework: Application to coupled electro-mechanics. Computer Physics Communications 216 (2017) 35\u201352.","DOI":"10.1016\/j.cpc.2017.02.016"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3071-5"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"David\u00a0E Rumelhart Geoffrey\u00a0E Hinton and Ronald\u00a0J Williams. 1986. Learning representations by back-propagating errors. Nature 323 6088 (1986) 533\u2013536.","DOI":"10.1038\/323533a0"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Sara Shashaani Fatemeh\u00a0S Hashemi and Raghu Pasupathy. 2018. ASTRO-DF: A class of adaptive sampling trust-region algorithms for derivative-free stochastic optimization. SIAM Journal on Optimization 28 4 (2018) 3145\u20133176.","DOI":"10.1137\/15M1042425"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"James\u00a0C Spall. 2002. Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Trans. Autom. Control 37 3 (2002) 332\u2013341.","DOI":"10.1109\/9.119632"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Eylem Tekin and Ihsan Sabuncuoglu. 2004. Simulation optimization: A comprehensive review on theory and applications. IIE trans. 36 11 (2004) 1067\u20131081.","DOI":"10.1080\/07408170490500654"},{"key":"e_1_3_3_2_35_2","unstructured":"Long Wang Qi Wang James\u00a0C Spall and Jingyi Zhu. 2025. Simultaneous perturbation stochastic approximation for mixed variables. IEEE Trans. Automat. Control (2025)."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Ronald\u00a0J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8 3 (1992) 229\u2013256.","DOI":"10.1023\/A:1022672621406"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3314139"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Haixiang Zhang Zeyu Zheng and Javad Lavaei. 2023. Gradient-based algorithms for convex discrete optimization via simulation. Operations research 71 5 (2023) 1815\u20131834.","DOI":"10.1287\/opre.2022.2295"},{"key":"e_1_3_3_2_39_2","unstructured":"Yaofeng\u00a0Desmond Zhong Jiequn Han and Georgia\u00a0Olympia Brikis. 2022. Differentiable physics simulations with contacts: Do they have correct gradients wrt position velocity and control? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.05060 (2022)."}],"event":{"name":"SIGSIM-PADS '26: 40th ACM SIGSIM Conference on Principles of Advanced Discrete Simulation","location":"Vienna , Austria","acronym":"SIGSIM-PADS '26","sponsor":["SIGSIM ACM Special Interest Group on Simulation and Modeling"]},"container-title":["Proceedings of the 40th ACM SIGSIM International Conference on Principles of Advanced Discrete Simulation"],"original-title":[],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T09:34:20Z","timestamp":1782207260000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806789.3810252"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":38,"alternative-id":["10.1145\/3806789.3810252","10.1145\/3806789"],"URL":"https:\/\/doi.org\/10.1145\/3806789.3810252","relation":{},"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"2026-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}