{"id":"https://openalex.org/W7164937842","doi":"https://doi.org/10.48550/arxiv.2606.15959","title":"Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling","display_name":"Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling","publication_year":2026,"publication_date":"2026-06-14","ids":{"openalex":"https://openalex.org/W7164937842","doi":"https://doi.org/10.48550/arxiv.2606.15959"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15959","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.15959","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138705400","display_name":"Zhimin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136712809","display_name":"Harshitha Menon","orcid":"https://orcid.org/0000-0003-4707-9580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Menon, Harshitha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125060179","display_name":"Charles Jekel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jekel, Charles","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009460413","display_name":"Valerio Pascucci","orcid":"https://orcid.org/0000-0002-8877-2042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pascucci, Valerio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138699123","display_name":"Peter Lindstrom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lindstrom, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.40860000252723694,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.40860000252723694,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.1655000001192093,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.08079999685287476,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.881600022315979},{"id":"https://openalex.org/keywords/surrogate-model","display_name":"Surrogate model","score":0.6366000175476074},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6074000000953674},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4973999857902527},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48899999260902405},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48030000925064087},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4715000092983246}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.881600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48899999260902405},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43380001187324524},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15959","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.15959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15959","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"networks":[1],"are":[2,12],"used":[3],"as":[4],"generative":[5,35,92],"surrogate":[6,36,93,130,158,182],"models":[7,19,37],"for":[8],"scientific":[9,16],"discovery,":[10],"which":[11,42],"trainable":[13],"approximations":[14],"of":[15,85,91,139,180,188],"simulations.":[17],"These":[18,160],"enable":[20],"users":[21],"to":[22,55,73,123,170,206],"replace":[23],"time-consuming":[24],"numerical":[25],"simulations":[26,142],"with":[27,174],"learned":[28],"alternatives,":[29],"providing":[30],"quick":[31],"solutions.":[32],"However,":[33],"high-fidelity":[34],"require":[38],"massive":[39],"training":[40,86,103,109,154,190,202],"datasets,":[41],"can":[43,111,132],"create":[44],"storage":[45,168],"and":[46,151,172,199],"I/O":[47],"challenges.":[48],"Lossy":[49],"compression":[50,60,84,165],"is":[51],"a":[52,121,129],"promising":[53],"way":[54],"reduce":[56],"this":[57,78,117],"burden,":[58],"but":[59],"errors":[61],"may":[62],"affect":[63],"the":[64,89,99,178,181,186,189,195,201],"model":[65,131],"quality":[66,90,179],"in":[67,102],"subtle":[68],"ways,":[69],"making":[70],"it":[71],"challenging":[72],"quantify":[74],"their":[75],"impact.":[76],"In":[77],"work,":[79],"we":[80,119],"examine":[81],"how":[82,125],"lossy":[83,164],"data":[87,167,191,196],"impacts":[88],"models.":[94,114,159],"We":[95],"begin":[96],"by":[97,204],"characterizing":[98],"uncertainty":[100],"inherent":[101],"neural":[104],"networks,":[105],"showing":[106],"that":[107,144,163],"identical":[108],"configurations":[110],"produce":[112],"different":[113],"By":[115],"exploiting":[116],"variability,":[118],"propose":[120],"method":[122],"estimate":[124],"much":[126],"compression-induced":[127],"error":[128],"tolerate":[133],"without":[134],"affecting":[135],"its":[136],"accuracy.":[137],"Evaluation":[138],"two":[140],"application":[141],"demonstrates":[143],"our":[145],"approach":[146],"significantly":[147],"reduces":[148,200],"memory/storage":[149],"requirements":[150],"speeds":[152],"up":[153,169,205],"while":[155],"producing":[156],"high-quality":[157],"results":[161],"show":[162],"saves":[166],"23.7x":[171],"39x":[173],"negligible":[175],"impact":[176],"on":[177],"model.":[183],"Meanwhile,":[184],"reducing":[185],"size":[187],"set":[192],"also":[193],"enhances":[194],"loading":[197],"speed":[198],"time":[203],"3x.":[207]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}