{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:12:17Z","timestamp":1783746737874,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"U.S. Department of Energy\u200c Office of Science\u200c Advanced Scientific Computing Research","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]},{"name":"U.S. Department of Energy\u200c Office of Science\u200c Advanced Scientific Computing Research","award":["DE-SC0025416"],"award-info":[{"award-number":["DE-SC0025416"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2344717"],"award-info":[{"award-number":["2344717"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,13]]},"DOI":"10.1145\/3806645.3815106","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:21:11Z","timestamp":1783743671000},"page":"207-220","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Information Theory and Practice for Scientific Lossy Compression"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4087-6907","authenticated-orcid":false,"given":"Sujata","family":"Sinha","sequence":"first","affiliation":[{"name":"Virginia Polytechnic Institute and State University, Alexandria, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9935-5674","authenticated-orcid":false,"given":"Sheng","family":"Di","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4395-6075","authenticated-orcid":false,"given":"Vishwas","family":"Rao","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1464-729X","authenticated-orcid":false,"given":"Robert","family":"Underwood","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2587-2783","authenticated-orcid":false,"given":"David","family":"Lenz","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2079-8130","authenticated-orcid":false,"given":"Zizhe","family":"Jian","sequence":"additional","affiliation":[{"name":"University of California Riverside, Riverside, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3232-4963","authenticated-orcid":false,"given":"Zhuoxun","family":"Yang","sequence":"additional","affiliation":[{"name":"Florida State Unviersity, Tallahassee, Florida, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5328-3962","authenticated-orcid":false,"given":"Kai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Florida State University, Tallahassee, Florida, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1915-1784","authenticated-orcid":false,"given":"Lingjia","family":"Liu","sequence":"additional","affiliation":[{"name":"Virginia Polytechnic Institute and State University, Alexandria, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7890-3934","authenticated-orcid":false,"given":"Franck","family":"Cappello","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Hirotugu Akaike. 2003. A new look at the statistical model identification. Transactions on Automatic Control 19 6 (2003) 716\u2013723.","DOI":"10.1109\/TAC.1974.1100705"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Yoav Benjamini and Yosef Hochberg. 1995. Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal statistical society: series B (Methodological) 57 1 (1995) 289\u2013300.","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_3_2_4_2","volume-title":"Rate Distortion Theory: A mathematical basis for data compression","author":"Berger Toby","year":"1971","unstructured":"Toby Berger. 1971. Rate Distortion Theory: A mathematical basis for data compression. Prentice-Hall, Englewood Cliffs, NJ."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Martin Burtscher and Paruj Ratanaworabhan. 2008. FPC: A high-speed compressor for double-precision floating-point data. IEEE Trans. Comput. 58 1 (2008) 18\u201331.","DOI":"10.1109\/TC.2008.131"},{"key":"e_1_3_3_2_6_2","unstructured":"Franck Cappello Allison Baker Ebru Bozda Martin Burtscher Kyle Chard Sheng Di Paul Christopher\u00a0O Grady Peng Jiang Shaomeng Li Erik Lindahl et\u00a0al. 2025. Lossy Compression of Scientific Data: Applications Constrains and Requirements. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20031 (2025)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/1064092.1064133"},{"key":"e_1_3_3_2_8_2","unstructured":"Yann Collet. 2015. Zstandard \u2013 Real-time data compression algorithm. http:\/\/facebook.github.io\/zstd\/ (2015)."},{"key":"e_1_3_3_2_9_2","volume-title":"Elements of Information Theory (2 ed.)","author":"Cover Thomas\u00a0M.","year":"2006","unstructured":"Thomas\u00a0M. Cover and Joy\u00a0A. Thomas. 2006. Elements of Information Theory (2 ed.). Wiley-Interscience, Hoboken, NJ."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781119241577"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.11"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Sheng Di Jinyang Liu Kai Zhao Xin Liang Robert Underwood Zhaorui Zhang Milan Shah Yafan Huang Jiajun Huang Xiaodong Yu et\u00a0al. 2025. A survey on error-bounded lossy compression for scientific datasets. ACM computing surveys 57 11 (2025) 1\u201338.","DOI":"10.1145\/3733104"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER52292.2023.00028"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/1996289"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"J. Hayes A. Habibi and P. Wintz. 1970. Rate-distortion function for a Gaussian source model of images (Corresp.). IEEE Transactions on Information Theory 16 4 (1970) 507\u2013509.","DOI":"10.1109\/TIT.1970.1054496"},{"key":"e_1_3_3_2_16_2","volume-title":"Bayesian Statistics 6","author":"Higdon David","year":"1998","unstructured":"David Higdon. 1998. A Process-Convolution Approach to Modeling Temperatures in the North Atlantic Ocean. In Bayesian Statistics 6, J.\u00a0M. Bernardo, J.\u00a0O. Berger, A.\u00a0P. Dawid, and A.\u00a0F.\u00a0M. Smith (Eds.). Oxford University Press."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656636"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00110"},{"key":"e_1_3_3_2_19_2","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis","author":"Huang Yafan","year":"2024","unstructured":"Yafan Huang, Sheng Di, Guanpeng Li, and Franck Cappello. 2024. cuSZp2: A GPU lossy compressor with extreme throughput and optimized compression ratio. In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis. IEEE, Article 15, 18\u00a0pages."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC58850.2023.00029"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Alexander Khintchine. 1934. Korrelationstheorie der station\u00e4ren stochastischen Prozesse. Math. Ann. 109 1 (1934) 604\u2013615.","DOI":"10.1007\/BF01449156"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Andrey Kolmogorov. 1956. On the Shannon theory of information transmission in the case of continuous signals. IRE Transactions on Information Theory 2 4 (1956) 102\u2013108.","DOI":"10.1109\/TIT.1956.1056823"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Victoria Kostina and Sergio Verd\u00fa. 2012. Fixed-length Lossy Compression in the Finite Blocklength Regime. IEEE Transactions on Information Theory 58 6 (2012) 3309\u20133338. 10.1109\/TIT.2012.2186786","DOI":"10.1109\/TIT.2012.2186786"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00104"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356193"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622520"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891037"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Xin Liang Ben Whitney Jieyang Chen Lipeng Wan Qing Liu Dingwen Tao James Kress David Pugmire Matthew Wolf Norbert Podhorszki et\u00a0al. 2021. Mgard+: Optimizing multilevel methods for error-bounded scientific data reduction. IEEE Trans. Comput. 71 7 (2021) 1522\u20131536.","DOI":"10.1109\/TC.2021.3092201"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Peter Lindstrom. 2014. Fixed-rate compressed floating-point arrays. IEEE Transactions on Visualization and Computer Graphics 20 12 (2014) 2674\u20132683.","DOI":"10.1109\/TVCG.2014.2346458"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Jinyang Liu Sheng Di Kai Zhao Xin Liang Sian Jin Zizhe Jian Jiajun Huang Shixun Wu Zizhong Chen and Franck Cappello. 2024. High-performance effective scientific error-bounded lossy compression with auto-tuned multi-component interpolation. Proceedings of the ACM on Management of Data 2 1 (2024) 1\u201327.","DOI":"10.1145\/3639259"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00064"},{"key":"e_1_3_3_2_32_2","volume-title":"Information theory, inference and learning algorithms","author":"MacKay David\u00a0JC","year":"2003","unstructured":"David\u00a0JC MacKay. 2003. Information theory, inference and learning algorithms. Cambridge university press."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Noa Malem-Shinitski Yingzhuo Zhang Daniel\u00a0T Gray Sara\u00a0N Burke Anne\u00a0C Smith Carol\u00a0A Barnes and Demba Ba. 2018. A separable two-dimensional random field model of binary response data from multi-day behavioral experiments. Journal of Neuroscience Methods 307 (2018) 175\u2013187.","DOI":"10.1016\/j.jneumeth.2018.04.006"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10826140"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00092"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Christopher\u00a0J Paciorek and Mark\u00a0J Schervish. 2006. Spatial modelling using a new class of nonstationary covariance functions. Environmetrics: The Official Journal of the International Environmetrics Society 17 5 (2006) 483\u2013506.","DOI":"10.1002\/env.785"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Yury Polyanskiy H.\u00a0Vincent Poor and Sergio Verdu. 2010. Channel Coding Rate in the Finite Blocklength Regime. IEEE Transactions on Information Theory 56 5 (2010) 2307\u20132359. 10.1109\/TIT.2010.2043769","DOI":"10.1109\/TIT.2010.2043769"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00102"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731599.3767375"},{"key":"e_1_3_3_2_40_2","volume-title":"Proceedings of the 35th International Conference on Massive Storage Systems and Technology","author":"Rahman Md\u00a0Hasanur","year":"2024","unstructured":"Md\u00a0Hasanur Rahman, Sheng Di, Guanpeng Li, and Franck Cappello. 2024. A generic and efficient framework for estimating lossy compressibility of scientific data. In Proceedings of the 35th International Conference on Massive Storage Systems and Technology. ACM."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Gideon Schwartz. 1978. Estimating the dimension of a model. The Annals of Statistics 6 (1978) 461\u2013464.","DOI":"10.1214\/aos\/1176344136"},{"key":"#cr-split#-e_1_3_3_2_42_2.1","doi-asserted-by":"crossref","unstructured":"Claude\u00a0E. Shannon. 1948. A Mathematical Theory of Communication. Bell System Technical Journal 27 3 (1948) 379-423. Part I","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"#cr-split#-e_1_3_3_2_42_2.2","doi-asserted-by":"crossref","unstructured":"Part II appears in vol. 27 no. 4 pp. 623-656 (1948).","DOI":"10.1002\/j.1538-7305.1948.tb00917.x"},{"key":"e_1_3_3_2_43_2","first-page":"142","volume-title":"IRE National Convention Record, Part 4","author":"Shannon Claude\u00a0E.","year":"1959","unstructured":"Claude\u00a0E. Shannon. 1959. Coding Theorems for a Discrete Source with a Fidelity Criterion. In IRE National Convention Record, Part 4. IRE, 142\u2013163."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Samuel\u00a0Sanford Shapiro and Martin\u00a0B Wilk. 1965. An analysis of variance test for normality (complete samples). Biometrika 52 3-4 (1965) 591\u2013611.","DOI":"10.1093\/biomet\/52.3-4.591"},{"key":"e_1_3_3_2_45_2","unstructured":"Sujata Sinha Vishwas Rao Robert Underwood David Lenz Sheng Di Franck Cappello and Lingjia Liu. 2026. Rate-Distortion Bounds for Heterogeneous Random Fields on Finite Lattices. arxiv:https:\/\/arXiv.org\/abs\/2603.09833\u00a0[cs.IT] https:\/\/arxiv.org\/abs\/2603.09833"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Seung\u00a0Woo Son Zhengzhang Chen William Hendrix Ankit Agrawal Wei-keng Liao and Alok Choudhary. 2014. Data compression for the exascale computing era-survey. Supercomputing Frontiers and Innovations 1 2 (2014) 76\u201388. 10.14529\/jsfi140205","DOI":"10.14529\/jsfi140205"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.115"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"E. Wong. 1968. Two-dimensional random fields and representation of images. SIAM J. Appl. Math. 16 4 (1968) 756\u2013770.","DOI":"10.1137\/0116062"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759798"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356155"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531473"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00145"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378449"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","unstructured":"Lin Zhou and Mehul Motani. 2023. Finite Blocklength Lossy Source Coding for Discrete Memoryless Sources. Foundations and Trends in Communications and Information Theory 20 3 (06 2023) 157\u2013389. 10.1561\/0100000134","DOI":"10.1561\/0100000134"},{"key":"e_1_3_3_2_55_2","unstructured":"Zlib. n. d.. zlib Compression Library. https:\/\/www.zlib.net\/. Online."}],"event":{"name":"HPDC '26: 35th International Symposium on High-Performance Parallel and Distributed Computing","location":"Cleveland USA","acronym":"HPDC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:22:54Z","timestamp":1783743774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806645.3815106"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":55,"alternative-id":["10.1145\/3806645.3815106","10.1145\/3806645"],"URL":"https:\/\/doi.org\/10.1145\/3806645.3815106","relation":{},"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"2026-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}