{"id":"https://openalex.org/W7161007650","doi":"https://doi.org/10.48550/arxiv.2605.11551","title":"VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck","display_name":"VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161007650","doi":"https://doi.org/10.48550/arxiv.2605.11551"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11551","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.11551","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034838344","display_name":"Aryan Gondkar","orcid":"https://orcid.org/0009-0007-8277-3240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gondkar, Aryan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135345059","display_name":"Hayder Radha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radha, Hayder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136059710","display_name":"Yiming Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Yiming","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.43560001254081726,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.43560001254081726,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4025999903678894,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.024800000712275505,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.8672999739646912},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.7369999885559082},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6802999973297119},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5543000102043152},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5023999810218811},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.4848000109195709},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.47029998898506165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.430400013923645},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.42170000076293945}],"concepts":[{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.8672999739646912},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.7369999885559082},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6802999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6039000153541565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021000146865845},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.4848000109195709},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25540000200271606},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11551","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.11551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11551","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":"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":{"Detecting":[0],"out-of-distribution":[1],"(OOD)":[2],"samples":[3,102],"is":[4,141],"critical":[5],"for":[6,41,195],"safe":[7],"deployment":[8],"of":[9],"neural":[10],"networks":[11],"in":[12],"safety-critical":[13],"applications.":[14],"While":[15],"maximum":[16],"softmax":[17],"probability":[18],"(MSP)":[19],"provides":[20],"a":[21,142],"simple":[22],"baseline,":[23],"it":[24],"lacks":[25],"theoretical":[26],"grounding":[27],"and":[28,38,73,82,130],"suffers":[29],"from":[30],"miscalibration.":[31],"We":[32,63],"propose":[33],"VNDUQE":[34],"(VIB-based":[35],"Novelty":[36],"Detection":[37],"Uncertainty":[39],"Quantification":[40],"Nondestructive":[42],"Evaluation),":[43],"which":[44,55,140],"investigates":[45],"novelty":[46,189],"detection":[47,76,89,95,112,121,190],"through":[48,60],"the":[49,156],"Deep":[50],"Variational":[51],"Information":[52],"Bottleneck":[53],"(VIB),":[54],"explicitly":[56],"constrains":[57],"information":[58,157],"flow":[59],"learned":[61],"representations.":[62],"train":[64],"VIB":[65],"models":[66],"on":[67,98,100,115],"MNIST":[68],"with":[69,183],"held-out":[70],"digit":[71,117],"classes":[72],"evaluate":[74],"OOD":[75],"using":[77],"information-theoretic":[78,169],"metrics:":[79],"KL":[80,91],"divergence":[81,92],"prediction":[83,107],"entropy.":[84],"Our":[85],"results":[86],"reveal":[87],"complementary":[88],"signals:":[90],"achieves":[93,126],"perfect":[94],"(100\\%":[96],"AUROC":[97,114,129],"noise)":[99],"far-OOD":[101],"(noise,":[103],"domain":[104],"shift),":[105],"while":[106],"entropy":[108],"excels":[109],"at":[110,135],"near-OOD":[111],"(94.7\\%":[113],"novel":[116],"classes).":[118],"A":[119],"parallel":[120],"strategy":[122],"combining":[123],"both":[124],"metrics":[125],"95.3\\%":[127],"average":[128],"92\\%":[131],"true":[132],"positive":[133,138],"rate":[134],"5\\%":[136],"false":[137],"rate,":[139],"32":[143],"percentage":[144],"point":[145],"improvement":[146],"over":[147],"baseline":[148],"MSP":[149],"(85.0\\%":[150],"AUROC,":[151],"60.1\\%":[152],"TPR).":[153],"Compression":[154],"via":[155],"bottleneck":[158],"principle":[159],"($\u03b2=10^{-3}$)":[160],"reduces":[161],"Expected":[162],"Calibration":[163],"Error":[164],"by":[165],"38\\%,":[166],"demonstrating":[167],"that":[168],"constraints":[170],"produce":[171],"fundamentally":[172],"more":[173],"reliable":[174],"uncertainty":[175],"estimates.":[176],"These":[177],"findings":[178],"directly":[179],"support":[180],"active":[181],"learning":[182],"expensive":[184],"computational":[185],"oracles,":[186],"where":[187],"well-calibrated":[188],"enables":[191],"principled":[192],"threshold":[193],"selection":[194],"oracle":[196],"queries.":[197]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}