{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:06:33Z","timestamp":1784228793644,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811231","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Taming optimization variance in compact neural shading networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8799-7119","authenticated-orcid":false,"given":"Benedikt","family":"Bitterli","sequence":"first","affiliation":[{"name":"NVIDIA, Redmond, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9870-6307","authenticated-orcid":false,"given":"Petrik","family":"Clarberg","sequence":"additional","affiliation":[{"name":"NVIDIA, Lund, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9281-8644","authenticated-orcid":false,"given":"Chris","family":"Cummings","sequence":"additional","affiliation":[{"name":"NVIDIA, Guildford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6526-0922","authenticated-orcid":false,"given":"Aaron","family":"Lefohn","sequence":"additional","affiliation":[{"name":"NVIDIA, Redmond, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9810-0306","authenticated-orcid":false,"given":"Steve","family":"Marschner","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, USA and NVIDIA, Ithaca, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-9584","authenticated-orcid":false,"given":"Jan","family":"Nov\u00e1k","sequence":"additional","affiliation":[{"name":"NVIDIA, Prague, Czech Republic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2978-2130","authenticated-orcid":false,"given":"Fabrice","family":"Rousselle","sequence":"additional","affiliation":[{"name":"NVIDIA, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4146-187X","authenticated-orcid":false,"given":"Andrea","family":"Weidlich","sequence":"additional","affiliation":[{"name":"NVIDIA, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6434-465X","authenticated-orcid":false,"given":"Tizian","family":"Zeltner","sequence":"additional","affiliation":[{"name":"NVIDIA, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.2312\/egs.20211015"},{"key":"e_1_3_3_3_3_1","volume-title":"Advances in Neural Information Processing Systems Workshops","author":"Devarakonda Aditya","year":"2017","unstructured":"Aditya Devarakonda, Maxim Naumov, and Michael Garland. 2017. AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks. In Advances in Neural Information Processing Systems Workshops. https:\/\/arxiv.org\/abs\/1712.02029"},{"key":"e_1_3_3_3_4_1","unstructured":"Wa\u00ebl Doulazmi Auguste Lehuger Marin Toromanoff Valentin Charraut Thibault Buhet and Fabien Moutarde. 2025. Multiple-Frequencies Population-Based Training. CoRR abs\/2506.03225 (2025). arxiv:https:\/\/arXiv.org\/abs\/2506.03225\u00a0[cs.LG] http:\/\/arxiv.org\/abs\/2506.03225"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530732"},{"key":"e_1_3_3_3_6_1","unstructured":"Stanislav Fort Huiyi Hu and Balaji Lakshminarayanan. 2020. Deep Ensembles: A Loss Landscape Perspective. arxiv:https:\/\/arXiv.org\/abs\/1912.02757\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1912.02757"},{"key":"e_1_3_3_3_7_1","volume-title":"International Conference on Learning Representations","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle and Michael Carbin. 2019. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"e_1_3_3_3_8_1","series-title":"Proceedings of Machine Learning Research","first-page":"249","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","volume":"9","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010a. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol.\u00a09). PMLR, 249\u2013256. https:\/\/proceedings.mlr.press\/v9\/glorot10a.html"},{"key":"e_1_3_3_3_9_1","series-title":"Proceedings of Machine Learning Research","first-page":"249","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","volume":"9","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010b. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol.\u00a09), Yee\u00a0Whye Teh and Mike Titterington (Eds.). PMLR, Chia Laguna Resort, Sardinia, Italy, 249\u2013256. https:\/\/proceedings.mlr.press\/v9\/glorot10a.html"},{"key":"e_1_3_3_3_10_1","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arxiv:https:\/\/arXiv.org\/abs\/1503.02531\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.05407"},{"key":"e_1_3_3_3_12_1","unstructured":"Max Jaderberg Valentin Dalibard Simon Osindero Wojciech\u00a0M. Czarnecki Jeff Donahue Ali Razavi Oriol Vinyals Tim Green Iain Dunning Karen Simonyan Chrisantha Fernando and Koray Kavukcuoglu. 2017. Population Based Training of Neural Networks. CoRR abs\/1711.09846 (2017). arxiv:https:\/\/arXiv.org\/abs\/1711.09846\u00a0[cs.LG] http:\/\/arxiv.org\/abs\/1711.09846"},{"key":"e_1_3_3_3_13_1","unstructured":"Kevin Jamieson and Ameet Talwalkar. 2015. Non-stochastic Best Arm Identification and Hyperparameter Optimization. arxiv:https:\/\/arXiv.org\/abs\/1502.07943\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1502.07943"},{"key":"e_1_3_3_3_14_1","volume-title":"SlangPy","author":"Kallweit Simon","year":"2025","unstructured":"Simon Kallweit, Chris Cummings, Benedikt Bitterli, Sai Bangaru, and Yong He. 2025. SlangPy. https:\/\/github.com\/shader-slang\/slangpy."},{"key":"e_1_3_3_3_15_1","unstructured":"Nitish\u00a0Shirish Keskar Dheevatsa Mudigere Jorge Nocedal Mikhail Smelyanskiy and Ping Tak\u00a0Peter Tang. 2017. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arxiv:https:\/\/arXiv.org\/abs\/1609.04836\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1609.04836"},{"key":"e_1_3_3_3_16_1","unstructured":"Diederik Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (12 2014)."},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","unstructured":"Alexandr Kuznetsov Milo\u0161 Ha\u0161an Zexiang Xu Ling-Qi Yan Bruce Walter Nima\u00a0Khademi Kalantari Steve Marschner and Ravi Ramamoorthi. 2019. Learning generative models for rendering specular microgeometry. ACM Trans. Graph. 38 6 Article 225 (Nov 2019). 10.1145\/3355089.3356525","DOI":"10.1145\/3355089.3356525"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","unstructured":"Alexandr Kuznetsov Krishna Mullia Zexiang Xu Milo\u0161 Ha\u0161an and Ravi Ramamoorthi. 2021. NeuMIP: multi-resolution neural materials. ACM Trans. Graph. 40 4 Article 175 (Jul 2021). 10.1145\/3450626.3459795","DOI":"10.1145\/3450626.3459795"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330649"},{"key":"e_1_3_3_3_20_1","unstructured":"Lisha Li Kevin Jamieson Giulia DeSalvo Afshin Rostamizadeh and Ameet Talwalkar. 2018. Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization. Journal of Machine Learning Research 18 185 (2018) 1\u201352. http:\/\/jmlr.org\/papers\/v18\/16-558.html"},{"key":"e_1_3_3_3_21_1","unstructured":"Zhuang Liu Jianguo Li Zhiqiang Shen Gao Huang Shoumeng Yan and Changshui Zhang. 2017. Learning Efficient Convolutional Networks through Network Slimming. arxiv:https:\/\/arXiv.org\/abs\/1708.06519\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1708.06519"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","unstructured":"Lu Lu Yeonjong Shin Yanhui Su and George Em\u00a0Karniadakis. 2020. Dying ReLU and Initialization: Theory and Numerical Examples. Communications in Computational Physics 28 5 (June 2020) 1671\u20131706. 10.4208\/cicp.oa-2020-0165","DOI":"10.4208\/cicp.oa-2020-0165"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1087"},{"key":"e_1_3_3_3_24_1","unstructured":"Sam McCandlish Jared Kaplan Dario Amodei and Tom\u00a0B. Brown. 2018. An Empirical Model of Large-Batch Training. CoRR abs\/1812.06162 (2018). arxiv:https:\/\/arXiv.org\/abs\/1812.06162\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1812.06162"},{"key":"e_1_3_3_3_25_1","volume-title":"Proceedings of ICLR","author":"Mishkin D.","year":"2016","unstructured":"D. Mishkin and J. Matas. 2016. All you need is a good init. In Proceedings of ICLR."},{"key":"e_1_3_3_3_26_1","unstructured":"NVIDIA. 2023. da Vinci\u2019s Workshop. https:\/\/docs.omniverse.nvidia.com\/usd\/latest\/usd_content_samples\/davinci_workshop.html#da-vinci-s-workshop"},{"key":"e_1_3_3_3_27_1","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Pham Nghia","year":"2023","unstructured":"Nghia Pham and Kevin Duh. 2023. A Hyperparameter Optimization Toolkit for Neural Machine Translation Research. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics, Toronto, Canada."},{"key":"e_1_3_3_3_28_1","unstructured":"Pixar. 2019. USDPreviewSurface. https:\/\/openusd.org\/release\/spec_usdpreviewsurface.html"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","unstructured":"Gilles Rainer Abhijeet Ghosh Wenzel Jakob and Tim Weyrich. 2020. Unified Neural Encoding of BTFs. Computer Graphics Forum 39 2 167\u2013178. 10.1111\/cgf.13921","DOI":"10.1111\/cgf.13921"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","unstructured":"Gilles Rainer Wenzel Jakob Abhijeet Ghosh and Tim Weyrich. 2019. Neural BTF Compression and Interpolation. Computer Graphics Forum 38 2 235\u2013244. 10.1111\/cgf.13633","DOI":"10.1111\/cgf.13633"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-6453-2_2"},{"key":"e_1_3_3_3_32_1","unstructured":"Gil\u00a0I. Shamir Dong Lin and Lorenzo Coviello. 2020. Smooth activations and reproducibility in deep networks. arxiv:https:\/\/arXiv.org\/abs\/2010.09931\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2010.09931"},{"key":"e_1_3_3_3_33_1","unstructured":"Samuel\u00a0L. Smith Pieter-Jan Kindermans Chris Ying and Quoc\u00a0V. Le. 2018. Don\u2019t Decay the Learning Rate Increase the Batch Size. arxiv:https:\/\/arXiv.org\/abs\/1711.00489\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1711.00489"},{"key":"e_1_3_3_3_34_1","first-page":"1139","volume-title":"International conference on machine learning","author":"Sutskever Ilya","year":"2013","unstructured":"Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. 2013. On the importance of initialization and momentum in deep learning. In International conference on machine learning. PMLR, 1139\u20131147."},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","unstructured":"Alejandro Sztrajman Gilles Rainer Tobias Ritschel and Tim Weyrich. 2021. Neural BRDF Representation and Importance Sampling. Computer Graphics Forum 40 6 332\u2013346. 10.1111\/cgf.14335","DOI":"10.1111\/cgf.14335"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","unstructured":"Justus Thies Michael Zollh\u00f6fer and Matthias Nie\u00dfner. 2019. Deferred neural rendering: image synthesis using neural textures. ACM Trans. Graph. 38 4 Article 66 (Jul 2019). 10.1145\/3306346.3323035","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","unstructured":"Lorenzo Valerio Franco\u00a0Maria Nardini Andrea Passarella and Raffaele Perego. 2022. Dynamic Hard Pruning of Neural Networks at the Edge of the Internet. Journal of Network and Computer Applications 200 (2022). 10.1016\/j.jnca.2021.103330","DOI":"10.1016\/j.jnca.2021.103330"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757374.3771447"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","unstructured":"Bowen Xue Shuang Zhao Henrik\u00a0Wann Jensen and Zahra Montazeri. 2024. A Hierarchical Architecture for Neural Materials. Computer Graphics Forum 43 6 (2024) e15116. arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.1511610.1111\/cgf.15116","DOI":"10.1111\/cgf.15116"},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"publisher","unstructured":"Tizian Zeltner Fabrice Rousselle Andrea Weidlich Petrik Clarberg Jan Nov\u00e1k Benedikt Bitterli Alex Evans Tom\u00e1\u0161 Davidovi\u010d Simon Kallweit and Aaron Lefohn. 2024. Real-Time Neural Appearance Models. ACM Trans. Graph. 43 3 Article 33 (Jun 2024). 10.1145\/3659577","DOI":"10.1145\/3659577"},{"key":"e_1_3_3_3_41_1","first-page":"130","volume-title":"Proc. of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1)","author":"Zhang Xuan","year":"2024","unstructured":"Xuan Zhang and Kevin Duh. 2024. Best Practices of Successive Halving on Neural Machine Translation and Large Language Models. In Proc. of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1). 130\u2013139."},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","unstructured":"Chuankun Zheng Ruzhang Zheng Rui Wang Shuang Zhao and Hujun Bao. 2021. A Compact Representation of Measured BRDFs Using Neural Processes. ACM Trans. Graph. 41 2 Article 14 (Nov 2021). 10.1145\/3490385","DOI":"10.1145\/3490385"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:25:56Z","timestamp":1784226356000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811231"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":41,"alternative-id":["10.1145\/3799902.3811231","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811231","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}