{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:56:09Z","timestamp":1782496569639,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T00:00:00Z","timestamp":1782604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"German Federal Ministry of Research, Technology and Space (BMFTR)","award":["01IS22068 EQUIPE"],"award-info":[{"award-number":["01IS22068 EQUIPE"]}]},{"name":"German Federal Ministry of Research, Technology and Space (BMFTR)","award":["01LK2313A SMARTWEATHER21"],"award-info":[{"award-number":["01LK2313A SMARTWEATHER21"]}]},{"DOI":"10.13039\/501100009318","name":"Helmholtz Association","doi-asserted-by":"publisher","award":["Helmholtz AI Platform Grant"],"award-info":[{"award-number":["Helmholtz AI Platform Grant"]}],"id":[{"id":"10.13039\/501100009318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3815572.3815745","type":"proceedings-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:44:02Z","timestamp":1782495842000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sampling Parallelism for Fast and Efficient Bayesian Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2808-4744","authenticated-orcid":false,"given":"Asena Karolin","family":"\u00d6zdemir","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7949-1858","authenticated-orcid":false,"given":"Lars Helge","family":"Heyen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2684-0927","authenticated-orcid":false,"given":"Arvid","family":"Weyrauch","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5065-469X","authenticated-orcid":false,"given":"Achim","family":"Streit","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2233-1041","authenticated-orcid":false,"given":"Markus","family":"G\u00f6tz","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany and Helmholtz AI, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7156-2022","authenticated-orcid":false,"given":"Charlotte","family":"Debus","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3163384"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00180-024-01561-7"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06185-3"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1622","author":"Blundell Charles","year":"2015","unstructured":"Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra. 2015. Weight Uncertainty in Neural Network. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37), Francis Bach and David Blei (Eds.). PMLR, Lille, France, 1613\u20131622. https:\/\/proceedings.mlr.press\/v37\/blundell15.html"},{"key":"e_1_3_2_1_5_1","unstructured":"Felix Brakel Uraz Odyurt and Ana-Lucia Varbanescu. 2024. Model parallelism on distributed infrastructure: A literature review from theory to LLM case-studies. arXiv:2403.03699 [cs.DC]"},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR","author":"Chowdhury Arkabandhu","year":"2018","unstructured":"Arkabandhu Chowdhury and Christopher Jermaine. 2018. Parallel and distributed MCMC via shepherding distributions. In International Conference on Artificial Intelligence and Statistics. PMLR, 1819\u20131827."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16\u00d716 Words: Transformers for Image Recognition at Scale. arXiv:2010.11929 [cs.CV] doi:10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"e_1_3_2_1_9_1","unstructured":"ENTSO-E. 2025. Germany - Load Data Transparency Platform. https:\/\/transparency.entsoe.eu\/."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of The 33rd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proceedings of The 33rd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 48), Maria Florina Balcan and Kilian Q. Weinberger (Eds.). PMLR, New York, New York, USA, 1050\u20131059. https:\/\/proceedings.mlr.press\/v48\/gal16.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10562-9"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2018. Accurate Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv:1706.02677 [cs.CV] doi:10.48550\/arXiv.1706.02677","DOI":"10.48550\/arXiv.1706.02677"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986721"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Hans Hersbach Bill Bell Paul Berrisford Shoji Hirahara Andr\u00e1s Hor\u00e1nyi Joaqu\u00edn Mu\u00f1oz-Sabater Julien Nicolas Carole Peubey Raluca Radu Dinand Schepers et al. 2020. The ERA5 global reanalysis. Quarterly journal of the royal meteorological society 146 730 (2020) 1999\u20132049. doi:10.1002\/qj.3803","DOI":"10.1002\/qj.3803"},{"key":"e_1_3_2_1_16_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840\u20136851."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Hoffmann Jordan","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, Tom Hennigan, Eric Noland, Katie Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karen Simonyan, Erich Elsen, Oriol Vinyals, Jack W. Rae, and Laurent Sifre. 2022. Training compute-optimal large language models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 2176, 15 pages."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: efficient training of giant neural networks using pipeline parallelism. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 10, 10 pages."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin \u017d\u00eddek Anna Potapenko et al. 2021. Highly accurate protein structure prediction with AlphaFold. nature 596 7873 (2021) 583\u2013589. doi:10.1038\/s41586-021-03819-2","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Kendall Alex","unstructured":"Alex Kendall and Yarin Gal.2017. What uncertainties do we need in Bayesian deep learning for computer vision?. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 5580\u20135590."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Nitish Shirish Keskar Dheevatsa Mudigere Jorge Nocedal Mikhail Smelyanskiy and Ping Tak Peter Tang. 2017. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv:1609.04836 [cs.LG] doi:10.48550\/arXiv.1609.04836","DOI":"10.48550\/arXiv.1609.04836"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adl2528"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592979.3593412"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295387"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Remi Lam Alvaro Sanchez-Gonzalez Matthew Willson Peter Wirnsberger Meire Fortunato Ferran Alet Suman Ravuri Timo Ewalds Zach Eaton-Rosen Weihua Hu et al. 2023. Learning skillful medium-range global weather forecasting. Science 382 6677 (2023) 1416\u20131421. doi:10.1126\/science.adi2336","DOI":"10.1126\/science.adi2336"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Christian Lessig Ilaria Luise Bing Gong Michael Langguth Scarlet Stadtler and Martin Schultz. 2023. AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learning. arXiv:2308.13280 [physics.ao-ph] doi:10.48550\/arXiv.2308.13280","DOI":"10.48550\/arXiv.2308.13280"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455466"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036322"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc.","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00d6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: an imperative style, high-performance deep learning library. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 721, 12 pages."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08252-9"},{"key":"e_1_3_2_1_34_1","unstructured":"RAI-SCC. 2025. torch_blue. https:\/\/github.com\/RAI-SCC\/torch_blue."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1029\/2023MS004019"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0188"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv:1909.08053 [cs.CL] doi:10.48550\/arXiv.1909.08053","DOI":"10.48550\/arXiv.1909.08053"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-17-8873-2024"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","unstructured":"Matias Valdenegro-Toro and Radina Stoykova. 2024. The Dilemma of Uncertainty Estimation for General Purpose AI in the EU AI Act. arXiv:2408.11249 [cs.AI] doi:10.48550\/arXiv.2408.11249","DOI":"10.48550\/arXiv.2408.11249"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Yanli Zhao Andrew Gu Rohan Varma Liang Luo Chien-Chin Huang Min Xu Less Wright Hamid Shojanazeri Myle Ott Sam Shleifer Alban Desmaison Can Balioglu Pritam Damania Bernard Nguyen Geeta Chauhan Yuchen Hao Ajit Mathews and Shen Li. 2023. PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel. arXiv:2304.11277 [cs.DC] doi:10.48550\/arXiv.2304.11277","DOI":"10.48550\/arXiv.2304.11277"}],"event":{"name":"PASC '26: Platform for Advanced Scientific Computing Conference","location":"Bern Switzerland","acronym":"PASC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the Platform for Advanced Scientific Computing Conference"],"original-title":[],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:45:16Z","timestamp":1782495916000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3815572.3815745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,28]]},"references-count":41,"alternative-id":["10.1145\/3815572.3815745","10.1145\/3815572"],"URL":"https:\/\/doi.org\/10.1145\/3815572.3815745","relation":{},"subject":[],"published":{"date-parts":[[2026,6,28]]},"assertion":[{"value":"2026-06-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}