{"id":"https://openalex.org/W7161171438","doi":"https://doi.org/10.48550/arxiv.2605.13788","title":"Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs","display_name":"Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161171438","doi":"https://doi.org/10.48550/arxiv.2605.13788"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13788","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.13788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093642950","display_name":"Eszter Varga-Umbrich","orcid":"https://orcid.org/0000-0003-2871-8965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varga-Umbrich, Eszter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015974223","display_name":"Zachary Weller-Davies","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weller-Davies, Zachary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063524295","display_name":"Paul Duckworth","orcid":"https://orcid.org/0000-0001-9052-6919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duckworth, Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001492871","display_name":"Jules Tilly","orcid":"https://orcid.org/0000-0001-5034-474X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tilly, Jules","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049412905","display_name":"Olivier Peltre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peltre, Olivier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034039171","display_name":"Shikha Surana","orcid":"https://orcid.org/0009-0007-1701-6876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Surana, Shikha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9549999833106995,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9549999833106995,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0027000000700354576,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6988999843597412},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6101999878883362},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5821999907493591},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5266000032424927},{"id":"https://openalex.org/keywords/tangent","display_name":"Tangent","score":0.4848000109195709},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4657999873161316},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.40939998626708984}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6988999843597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6104000210762024},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6101999878883362},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206999778747559},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.40939998626708984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.2809999883174896},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13788","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.13788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13788","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8101963996887207}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Active":[0],"learning":[1,221],"for":[2,120,222],"machine-learning":[3],"interatomic":[4],"potentials":[5],"(MLIPs)":[6],"must":[7],"address":[8,40],"several":[9],"challenges":[10],"to":[11,15,31,79,98],"be":[12],"practical:":[13],"scaling":[14,48],"large":[16],"candidate":[17,26,62],"pools,":[18],"leveraging":[19],"energy-force":[20,113,130],"supervision,":[21],"and":[22,63,76,110,146,149,154,160,195,218],"maintaining":[23],"robustness":[24],"when":[25],"pools":[27],"are":[28],"biased":[29],"relative":[30],"the":[32,61,93,125,128,133,143],"target":[33],"distribution.":[34],"In":[35],"this":[36,67],"work,":[37],"we":[38],"jointly":[39],"these":[41,206],"challenges.":[42],"We":[43,90,123],"first":[44],"introduce":[45],"a":[46,99,107,111,181,210],"linearly":[47],"acquisition":[49,80,138,189],"framework":[50],"based":[51,85,190],"on":[52,86,132,187,191],"chunked":[53],"feature-space":[54],"posterior-variance":[55],"shortlisting.":[56],"By":[57],"avoiding":[58],"materialisation":[59],"of":[60,71,127],"train":[64],"set":[65],"kernels,":[66],"approach":[68],"enables":[69],"screening":[70],"~200k":[72],"structures":[73],"within":[74],"hours":[75],"applies":[77],"broadly":[78],"strategies":[81],"that":[82,115,209],"score":[83],"candidates":[84],"molecular":[87],"similarity":[88,118],"metrics.":[89],"then":[91],"extend":[92],"Neural":[94],"Tangent":[95],"Kernel":[96],"(NTK)":[97],"force-aware":[100,137],"setting":[101],"via":[102],"mixed":[103],"parameter-coordinate":[104],"derivatives,":[105],"yielding":[106],"force":[108,147,164],"NTK":[109,114,131,165],"joint":[112,129],"provide":[116],"natural":[117],"metrics":[119,153],"vector-field":[121],"prediction.":[122],"demonstrate":[124],"effectiveness":[126],"OC20":[134],"dataset,":[135],"where":[136],"is":[139],"crucial:":[140],"it":[141],"achieves":[142],"lowest":[144],"energy":[145],"MAE":[148],"RMSE":[150],"across":[151],"all":[152],"distribution":[155],"splits.":[156],"Across":[157],"T1x,":[158,188],"PMechDB,":[159],"RGD":[161],"benchmarks,":[162],"our":[163],"methods":[166,201],"remain":[167],"competitive":[168],"with":[169],"established":[170],"baselines":[171],"while":[172],"being":[173],"significantly":[174],"more":[175],"efficient":[176],"than":[177],"committee-based":[178,200],"approaches.":[179],"Under":[180],"controlled":[182],"candidate-pool":[183],"shift":[184],"case":[185],"study":[186],"pretrained":[192,212],"MLIP":[193,213],"embeddings":[194],"NTKs":[196],"remains":[197],"robust,":[198],"whereas":[199],"exhibit":[202],"higher":[203],"variance.":[204],"Overall,":[205],"results":[207],"show":[208],"single":[211],"can":[214],"enable":[215],"scalable,":[216],"force-aware,":[217],"distribution-robust":[219],"active":[220],"foundation-model":[223],"fine-tuning.":[224]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-15T00:00:00"}