{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T02:10:01Z","timestamp":1774059001029,"version":"3.50.1"},"reference-count":101,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019827","name":"Meta","doi-asserted-by":"publisher","award":["5034015"],"award-info":[{"award-number":["5034015"]}],"id":[{"id":"10.13039\/100019827","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2024,7,19]]},"abstract":"<jats:p>\n            Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be applied to problems with undefined or zero gradients. To circumvent this issue, the loss function can be manually replaced by a \"surrogate\" that has similar minima but is differentiable. Our proposed framework,\n            <jats:italic>ZeroGrads<\/jats:italic>\n            , automates this process by learning a neural approximation of the objective function, which in turn can be used to differentiate through arbitrary black-box graphics pipelines. We train the surrogate on an actively smoothed version of the objective and encourage locality, focusing the surrogate's capacity on what matters at the current training episode. The fitting is performed online, alongside the parameter optimization, and self-supervised, without pre-computed data or pre-trained models. As sampling the objective is expensive (it requires a full rendering or simulator run), we devise an efficient sampling scheme that allows for tractable run-times and competitive performance at little overhead. We demonstrate optimizing diverse non-convex, non-differentiable black-box problems in graphics, such as visibility in rendering, discrete parameter spaces in procedural modelling or optimal control in physics-driven animation. In contrast to other derivative-free algorithms, our approach scales well to higher dimensions, which we demonstrate on problems with up to 35k interlinked variables.\n          <\/jats:p>","DOI":"10.1145\/3658173","type":"journal-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T14:47:57Z","timestamp":1721400477000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["ZeroGrads: Learning Local Surrogates for Non-Differentiable Graphics"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2610-4831","authenticated-orcid":false,"given":"Michael","family":"Fischer","sequence":"first","affiliation":[{"name":"University College London (UCL), London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4660-7790","authenticated-orcid":false,"given":"Tobias","family":"Ritschel","sequence":"additional","affiliation":[{"name":"University College London (UCL), London, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2024,7,19]]},"reference":[{"key":"e_1_2_2_1_1","first-page":"8675","article-title":"Autoinverse: Uncertainty aware inversion of neural networks","volume":"35","author":"Ansari Navid","year":"2022","unstructured":"Navid Ansari, Hans-Peter Seidel, Nima Vahidi Ferdowsi, and Vahid Babaei. 2022. Autoinverse: Uncertainty aware inversion of neural networks. Advances in Neural Information Processing Systems 35 (2022), 8675--8686.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618353"},{"key":"e_1_2_2_3_1","volume-title":"Differentiable Rendering of Neural SDFs through Reparameterization. arXiv preprint arXiv:2206.05344","author":"Bangaru Sai Praveen","year":"2022","unstructured":"Sai Praveen Bangaru, Micha\u00ebl Gharbi, Tzu-Mao Li, Fujun Luan, Kalyan Sunkavalli, Milo\u0161 Ha\u0161an, Sai Bi, Zexiang Xu, Gilbert Bernstein, and Fr\u00e9do Durand. 2022. Differentiable Rendering of Neural SDFs through Reparameterization. arXiv preprint arXiv:2206.05344 (2022)."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459775"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.1994.717134"},{"key":"e_1_2_2_6_1","volume-title":"Optimization without Backpropagation. arXiv preprint arXiv:2209.06302","author":"Belouze Gabriel","year":"2022","unstructured":"Gabriel Belouze. 2022. Optimization without Backpropagation. arXiv preprint arXiv:2209.06302 (2022)."},{"key":"e_1_2_2_7_1","volume-title":"Learning with differentiable pertubed optimizers. Advances in neural information processing systems 33","author":"Berthet Quentin","year":"2020","unstructured":"Quentin Berthet, Mathieu Blondel, Olivier Teboul, Marco Cuturi, Jean-Philippe Vert, and Francis Bach. 2020. Learning with differentiable pertubed optimizers. Advances in neural information processing systems 33 (2020), 9508--9519."},{"key":"e_1_2_2_8_1","volume-title":"Empirical model-building and response surfaces","author":"Box George EP","unstructured":"George EP Box and Norman R Draper. 1987. Empirical model-building and response surfaces. John Wiley & Sons."},{"key":"e_1_2_2_9_1","volume-title":"Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang.","author":"Bradbury James","year":"2018","unstructured":"James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang. 2018. JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/google\/jax"},{"key":"e_1_2_2_10_1","volume-title":"An Unexpected Challenge in Using Forward-Mode Automatic Differentiation for Low-Memory Deep Learning. Undergrad Theses","author":"Chandra Kartik","year":"2021","unstructured":"Kartik Chandra. 2021. An Unexpected Challenge in Using Forward-Mode Automatic Differentiation for Low-Memory Deep Learning. Undergrad Theses (2021)."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530715"},{"key":"e_1_2_2_12_1","volume-title":"A compositional object-based approach to learning physical dynamics. arXiv preprint arXiv:1612.00341","author":"Chang Michael B","year":"2016","unstructured":"Michael B Chang, Tomer Ullman, Antonio Torralba, and Joshua B Tenenbaum. 2016. A compositional object-based approach to learning physical dynamics. arXiv preprint arXiv:1612.00341 (2016)."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1809028.1806629"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3182162"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530714"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1137\/110831659"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.48"},{"key":"e_1_2_2_19_1","volume-title":"NICER: Aesthetic image enhancement with humans in the loop. arXiv preprint arXiv:2012.01778","author":"Fischer Michael","year":"2020","unstructured":"Michael Fischer, Konstantin Kobs, and Andreas Hotho. 2020. NICER: Aesthetic image enhancement with humans in the loop. arXiv preprint arXiv:2012.01778 (2020)."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555458"},{"key":"e_1_2_2_21_1","volume-title":"Plateau-free Differentiable Path Tracing. arXiv preprint arXiv:2211.17263","author":"Fischer Michael","year":"2022","unstructured":"Michael Fischer and Tobias Ritschel. 2022b. Plateau-free Differentiable Path Tracing. arXiv preprint arXiv:2211.17263 (2022)."},{"key":"e_1_2_2_22_1","volume-title":"Recent advances in surrogate-based optimization. Progress in aerospace sciences 45, 1--3","author":"Forrester Alexander IJ","year":"2009","unstructured":"Alexander IJ Forrester and Andy J Keane. 2009. Recent advances in surrogate-based optimization. Progress in aerospace sciences 45, 1--3 (2009), 50--79."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00727"},{"key":"e_1_2_2_24_1","volume-title":"Learning surrogate losses. arXiv preprint arXiv:1905.10108","author":"Grabocka Josif","year":"2019","unstructured":"Josif Grabocka, Randolf Scholz, and Lars Schmidt-Thieme. 2019. Learning surrogate losses. arXiv preprint arXiv:1905.10108 (2019)."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280816"},{"key":"e_1_2_2_26_1","volume-title":"Matformer: A generative model for procedural materials. arXiv preprint arXiv:2207.01044","author":"Guerrero Paul","year":"2022","unstructured":"Paul Guerrero, Milo\u0161 Ha\u0161an, Kalyan Sunkavalli, Radom\u00edr M\u011bch, Tamy Boubekeur, and Niloy J Mitra. 2022. Matformer: A generative model for procedural materials. arXiv preprint arXiv:2207.01044 (2022)."},{"key":"e_1_2_2_27_1","volume-title":"A radial basis function method for global optimization. J global optimization 19, 3","author":"Gutmann H-M","year":"2001","unstructured":"H-M Gutmann. 2001. A radial basis function method for global optimization. J global optimization 19, 3 (2001), 201--227."},{"key":"e_1_2_2_28_1","first-page":"484","article-title":"A history of the unity game engine","volume":"483","author":"Haas John K","year":"2014","unstructured":"John K Haas. 2014. A history of the unity game engine. Diss. WORCESTER POLYTECHNIC INSTITUTE 483 (2014), 484.","journal-title":"Diss. WORCESTER POLYTECHNIC INSTITUTE"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459749"},{"key":"e_1_2_2_30_1","volume-title":"The CMA evolution strategy: A tutorial. arXiv preprint arXiv:1604.00772","author":"Hansen Nikolaus","year":"2016","unstructured":"Nikolaus Hansen. 2016. The CMA evolution strategy: A tutorial. arXiv preprint arXiv:1604.00772 (2016)."},{"key":"e_1_2_2_31_1","volume-title":"Learning to control pdes with differentiable physics. arXiv preprint arXiv:2001.07457","author":"Holl Philipp","year":"2020","unstructured":"Philipp Holl, Vladlen Koltun, and Nils Thuerey. 2020. Learning to control pdes with differentiable physics. arXiv preprint arXiv:2001.07457 (2020)."},{"key":"e_1_2_2_32_1","series-title":"SIAM journal on computing 2, 2","volume-title":"Genetic algorithms and the optimal allocation of trials","author":"Holland John H","year":"1973","unstructured":"John H Holland. 1973. Genetic algorithms and the optimal allocation of trials. SIAM journal on computing 2, 2 (1973), 88--105."},{"key":"e_1_2_2_33_1","volume-title":"Difftaichi: Differentiable programming for physical simulation. arXiv preprint arXiv:1910.00935","author":"Hu Yuanming","year":"2019","unstructured":"Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, and Fr\u00e9do Durand. 2019. Difftaichi: Differentiable programming for physical simulation. arXiv preprint arXiv:1910.00935 (2019)."},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530733"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502431"},{"key":"e_1_2_2_36_1","unstructured":"Wenzel Jakob S\u00e9bastien Speierer Nicolas Roussel Merlin Nimier-David Delio Vicini Tizian Zeltner Baptiste Nicolet Miguel Crespo Vincent Leroy and Ziyi Zhang. 2022b. Mitsuba 3 Renderer 2022."},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530099"},{"key":"e_1_2_2_38_1","volume-title":"Query complexity of derivative-free optimization. Advances in Neural Information Processing Systems 25","author":"Jamieson Kevin G","year":"2012","unstructured":"Kevin G Jamieson, Robert Nowak, and Ben Recht. 2012. Query complexity of derivative-free optimization. Advances in Neural Information Processing Systems 25 (2012)."},{"key":"e_1_2_2_39_1","volume-title":"Efficient global optimization of expensive black-box functions. J Global optimization 13, 4","author":"Jones Donald R","year":"1998","unstructured":"Donald R Jones, Matthias Schonlau, and William J Welch. 1998. Efficient global optimization of expensive black-box functions. J Global optimization 13, 4 (1998), 455--92."},{"key":"e_1_2_2_40_1","volume-title":"See also NSA 3--990","author":"Kahn Herman","year":"1950","unstructured":"Herman Kahn. 1950. Random sampling (Monte Carlo) techniques in neutron attenuation problems. I. Nucleonics (US) Ceased publication 6, See also NSA 3--990 (1950)."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"e_1_2_2_43_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_2_2_44_1","volume-title":"C Daniel Gelatt Jr, and Mario P Vecchi","author":"Kirkpatrick Scott","year":"1983","unstructured":"Scott Kirkpatrick, C Daniel Gelatt Jr, and Mario P Vecchi. 1983. Optimization by simulated annealing. science 220, 4598 (1983), 671--680."},{"key":"e_1_2_2_45_1","volume-title":"Philippe Bompas, and Mark Pauly.","author":"Kiser Thomas","year":"2013","unstructured":"Thomas Kiser, Michael Eigensatz, Minh Man Nguyen, Philippe Bompas, and Mark Pauly. 2013. Architectural caustics---controlling light with geometry. In Advances in architectural geometry 2012. Springer, 91--106."},{"key":"e_1_2_2_46_1","volume-title":"Simulation modeling and analysis","author":"Law Averill M","unstructured":"Averill M Law, W David Kelton, and W David Kelton. 2007. Simulation modeling and analysis. Vol. 3. Mcgraw-hill New York."},{"key":"e_1_2_2_47_1","first-page":"20398","article-title":"Differentiable rendering with perturbed optimizers","volume":"34","author":"Lidec Quentin Le","year":"2021","unstructured":"Quentin Le Lidec, Ivan Laptev, Cordelia Schmid, and Justin Carpentier. 2021. Differentiable rendering with perturbed optimizers. Advances in Neural Information Processing Systems 34 (2021), 20398--20409.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_48_1","unstructured":"Yann LeCun. 1998. The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/ (1998)."},{"key":"e_1_2_2_49_1","volume-title":"Proc. NeurIPS 31","author":"Lee Wonyeol","year":"2018","unstructured":"Wonyeol Lee, Hangyeol Yu, and Hongseok Yang. 2018. Reparameterization gradient for non-differentiable models. Proc. NeurIPS 31 (2018)."},{"key":"e_1_2_2_50_1","first-page":"1","article-title":"End-to-End Procedural Material Capture with Proxy-Free Mixed-Integer Optimization","volume":"42","author":"Li Beichen","year":"2023","unstructured":"Beichen Li, Liang Shi, and Wojciech Matusik. 2023. End-to-End Procedural Material Capture with Proxy-Free Mixed-Integer Optimization. ACM Transactions on Graphics (TOG) 42, 4 (2023), 1--15.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275055"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417763"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"e_1_2_2_54_1","volume-title":"Proc","author":"Loper Matthew M","unstructured":"Matthew M Loper and Michael J Black. 2014. OpenDR: An approximate differentiable renderer. In Proc. ECCV. Springer, 154--169."},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356510"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258887"},{"key":"e_1_2_2_57_1","volume-title":"Gradients are not all you need. arXiv preprint arXiv:2111.05803","author":"Metz Luke","year":"2021","unstructured":"Luke Metz, C Daniel Freeman, Samuel S Schoenholz, and Tal Kachman. 2021. Gradients are not all you need. arXiv preprint arXiv:2111.05803 (2021)."},{"key":"e_1_2_2_58_1","volume-title":"Monte Carlo Gradient Estimation in Machine Learning. J. Mach. Learn. Res. 21","author":"Mohamed Shakir","year":"2020","unstructured":"Shakir Mohamed, Mihaela Rosca, Michael Figurnov, and Andriy Mnih. 2020. Monte Carlo Gradient Estimation in Machine Learning. J. Mach. Learn. Res. 21 (2020)."},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160251"},{"key":"e_1_2_2_60_1","volume-title":"Proc. NeurIPS 31","author":"Mrowca Damian","year":"2018","unstructured":"Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li F Fei-Fei, Josh Tenenbaum, and Daniel L Yamins. 2018. Flexible neural representation for physics prediction. Proc. NeurIPS 31 (2018)."},{"key":"e_1_2_2_61_1","volume-title":"Andrew Stewart, Goran Fernlund, Anoush Poursartip, and Frank Wood.","author":"Munk Andreas","year":"2019","unstructured":"Andreas Munk, Adam \u015acibior, At\u0131l\u0131m G\u00fcne\u015f Baydin, Andrew Stewart, Goran Fernlund, Anoush Poursartip, and Frank Wood. 2019. Deep probabilistic surrogate networks for universal simulator approximation. arXiv preprint arXiv:1910.11950 (2019)."},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13225"},{"key":"e_1_2_2_63_1","volume-title":"Accelerating physics-based simulations using end-to-end neural network proxies: An application in oil reservoir modeling. Frontiers in big Data 2","author":"Navr\u00e1til Ji\u0159\u00ed","year":"2019","unstructured":"Ji\u0159\u00ed Navr\u00e1til, Alan King, Jesus Rios, Georgios Kollias, Ruben Torrado, and Andr\u00e9s Codas. 2019. Accelerating physics-based simulations using end-to-end neural network proxies: An application in oil reservoir modeling. Frontiers in big Data 2 (2019), 33."},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"e_1_2_2_65_1","volume-title":"Computer Graphics Forum","author":"Nguyen Chuong H","unstructured":"Chuong H Nguyen, Tobias Ritschel, Karol Myszkowski, Elmar Eisemann, and HansPeter Seidel. 2012. 3D material style transfer. In Computer Graphics Forum, Vol. 31. Wiley Online Library, 431--438."},{"key":"e_1_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480501"},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592139"},{"key":"e_1_2_2_68_1","volume-title":"Computer Graphics Forum","author":"Papas Marios","unstructured":"Marios Papas, Wojciech Jarosz, Wenzel Jakob, Szymon Rusinkiewicz, Wojciech Matusik, and Tim Weyrich. 2011. Goal-based caustics. In Computer Graphics Forum, Vol. 30. Wiley Online Library, 503--511."},{"key":"e_1_2_2_69_1","volume-title":"Vrahatis","author":"Parsopoulos Konstantinos E","year":"2002","unstructured":"Konstantinos E Parsopoulos and Michael N. Vrahatis. 2002. Recent approaches to global optimization problems through particle swarm optimization. Natural computing 1, 2 (2002), 235--306."},{"key":"e_1_2_2_70_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)."},{"key":"e_1_2_2_71_1","volume-title":"Proc","author":"Patel Yash","unstructured":"Yash Patel, Tom\u00e1\u0161 Hoda\u0148, and Ji\u0159\u00ed Matas. 2020. Learning surrogates via deep embedding. In Proc. ECCV. Springer, 205--221."},{"key":"e_1_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00397"},{"key":"e_1_2_2_73_1","volume-title":"Advances in optimization and numerical analysis","author":"Powell Michael JD","unstructured":"Michael JD Powell. 1994. A direct search optimization method that models the objective and constraint functions by linear interpolation. In Advances in optimization and numerical analysis. Springer, 51--67."},{"key":"e_1_2_2_74_1","volume-title":"Surrogate-based analysis and optimization. Progress in aerospace sciences 41, 1","author":"Queipo Nestor V","year":"2005","unstructured":"Nestor V Queipo, Raphael T Haftka, Wei Shyy, Tushar Goel, Rajkumar Vaidyanathan, and P Kevin Tucker. 2005. Surrogate-based analysis and optimization. Progress in aerospace sciences 41, 1 (2005), 1--28."},{"key":"e_1_2_2_75_1","volume-title":"International Conference on Machine Learning. PMLR, 5301--5310","author":"Rahaman Nasim","year":"2019","unstructured":"Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred Hamprecht, Yoshua Bengio, and Aaron Courville. 2019. On the spectral bias of neural networks. In International Conference on Machine Learning. PMLR, 5301--5310."},{"key":"e_1_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13633"},{"key":"e_1_2_2_77_1","volume-title":"Proc. ICML. PMLR, 4267--4276","author":"Rainforth Tom","year":"2018","unstructured":"Tom Rainforth, Rob Cornish, Hongseok Yang, Andrew Warrington, and Frank Wood. 2018. On nesting Monte Carlo estimators. In Proc. ICML. PMLR, 4267--4276."},{"key":"e_1_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00045"},{"key":"e_1_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.94"},{"key":"e_1_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-012-9951-y"},{"key":"e_1_2_2_81_1","volume-title":"Conference on Robot Learning. PMLR, 317--335","author":"Schenck Connor","year":"2018","unstructured":"Connor Schenck and Dieter Fox. 2018. Spnets: Differentiable fluid dynamics for deep neural networks. In Conference on Robot Learning. PMLR, 317--335."},{"key":"e_1_2_2_82_1","volume-title":"High-contrast computational caustic design. ACM Transactions on Graphics (TOG)","author":"Schwartzburg Yuliy","year":"2014","unstructured":"Yuliy Schwartzburg, Romain Testuz, Andrea Tagliasacchi, and Mark Pauly. 2014. High-contrast computational caustic design. ACM Transactions on Graphics (TOG) (2014)."},{"key":"e_1_2_2_83_1","first-page":"1","article-title":"Match: differentiable material graphs for procedural material capture","volume":"39","author":"Shi Liang","year":"2020","unstructured":"Liang Shi, Beichen Li, Milo\u0161 Ha\u0161an, Kalyan Sunkavalli, Tamy Boubekeur, Radomir Mech, and Wojciech Matusik. 2020. Match: differentiable material graphs for procedural material capture. ACM Trans. Graph. 39, 6 (2020), 1--15.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_84_1","first-page":"14650","article-title":"Black-box optimization with local generative surrogates","volume":"33","author":"Shirobokov Sergey","year":"2020","unstructured":"Sergey Shirobokov, Vladislav Belavin, Michael Kagan, Andrei Ustyuzhanin, and Atilim Gunes Baydin. 2020. Black-box optimization with local generative surrogates. Proc. NeurIPS 33 (2020), 14650--14662.","journal-title":"Proc. NeurIPS"},{"key":"e_1_2_2_85_1","volume-title":"Proc. Pacific Graphics. 1--6.","author":"Sin Ping Tat","year":"2021","unstructured":"Ping Tat Sin, Hiu Fung Ng, and Hong Va Leong. 2021. Neural Proxy: Empowering Neural Volume Rendering for Animation. In Proc. Pacific Graphics. 1--6."},{"key":"e_1_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.119632"},{"key":"e_1_2_2_87_1","unstructured":"Joe Staines and David Barber. 2013. Optimization by Variational Bounding.. In ESANN."},{"key":"e_1_2_2_88_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Suh Hyung Ju","year":"2022","unstructured":"Hyung Ju Suh, Max Simchowitz, Kaiqing Zhang, and Russ Tedrake. 2022b. Do differentiable simulators give better policy gradients?. In International Conference on Machine Learning. PMLR, 20668--20696."},{"key":"e_1_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146931"},{"key":"e_1_2_2_90_1","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik Matthew","year":"2020","unstructured":"Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, and Ren Ng. 2020. Fourier features let networks learn high frequency functions in low dimensional domains. Advances in Neural Information Processing Systems 33 (2020), 7537--7547.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322996"},{"key":"e_1_2_2_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555526"},{"key":"e_1_2_2_93_1","volume-title":"Robust Monte Carlo methods for light transport simulation","author":"Veach Eric","unstructured":"Eric Veach. 1998. Robust Monte Carlo methods for light transport simulation. Stanford University."},{"key":"e_1_2_2_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530139"},{"key":"e_1_2_2_95_1","volume-title":"Simulation-based optimization with surrogate models---application to supply chain management. Computers & chemical engineering 29, 6","author":"Wan Xiaotao","year":"2005","unstructured":"Xiaotao Wan, Joseph F Pekny, and Gintaras V Reklaitis. 2005. Simulation-based optimization with surrogate models---application to supply chain management. Computers & chemical engineering 29, 6 (2005), 1317--1328."},{"key":"e_1_2_2_96_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8 (1992), 229--256."},{"key":"e_1_2_2_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111411.1111439"},{"key":"e_1_2_2_98_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550454.3555479","article-title":"Differentiable Rendering using RGBXY Derivatives and Optimal Transport","volume":"41","author":"Xing Jiankai","year":"2022","unstructured":"Jiankai Xing, Fujun Luan, Ling-Qi Yan, Xuejun Hu, Houde Qian, and Kun Xu. 2022. Differentiable Rendering using RGBXY Derivatives and Optimal Transport. ACM Transactions on Graphics (TOG) 41, 6 (2022), 1--13.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618165"},{"key":"e_1_2_2_100_1","volume-title":"A scalable evolution strategy with directional Gaussian smoothing for blackbox optimization. arXiv preprint","author":"Zhang Jiaxin","year":"2020","unstructured":"Jiaxin Zhang, Hoang Tran, Dan Lu, and Guannan Zhang. 2020. A scalable evolution strategy with directional Gaussian smoothing for blackbox optimization. arXiv preprint (2020)."},{"key":"e_1_2_2_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01141"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658173","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:54Z","timestamp":1750291554000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,19]]},"references-count":101,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7,19]]}},"alternative-id":["10.1145\/3658173"],"URL":"https:\/\/doi.org\/10.1145\/3658173","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,19]]},"assertion":[{"value":"2024-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}