{"id":"https://openalex.org/W7158198253","doi":"https://doi.org/10.48550/arxiv.2604.24810","title":"A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks","display_name":"A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7158198253","doi":"https://doi.org/10.48550/arxiv.2604.24810"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24810","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24810","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.2604.24810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134865933","display_name":"Grigorios Papanikolaou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papanikolaou, Grigorios","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060088887","display_name":"Ioannis Kontopoulos","orcid":"https://orcid.org/0000-0001-9862-8944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kontopoulos, Ioannis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134874360","display_name":"Konstantinos Tserpes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tserpes, Konstantinos","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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.18170000612735748,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.18170000612735748,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.17810000479221344,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.06599999964237213,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6352999806404114},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6065999865531921},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5870000123977661},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5149000287055969},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47780001163482666},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.42640000581741333},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515000104904175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6352999806404114},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47780001163482666},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C167393769","wikidata":"https://www.wikidata.org/wiki/Q4680768","display_name":"Adaptive strategies","level":2,"score":0.26660001277923584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24810","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24810","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.2604.24810","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24810","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9148122668266296}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Edge":[0],"computing":[1,41],"environments":[2],"impose":[3],"strict":[4],"constraints":[5],"on":[6,48,133,143],"energy":[7,123],"consumption":[8],"and":[9,23,103,105,125,136,140,150,170,174,182],"latency,":[10],"making":[11],"the":[12,56,64,68,77,108,134,144,165,177],"deployment":[13],"of":[14,67,114,147,180],"deep":[15],"neural":[16,138],"networks":[17],"a":[18,111],"significant":[19],"challenge.":[20],"Therefore,":[21],"smart":[22],"adaptive":[24],"inference":[25],"strategies":[26,96,116,130,157],"that":[27,54,155],"dynamically":[28,75],"balance":[29],"computational":[30],"cost":[31],"or":[32],"latency":[33],"with":[34,117,162],"predictive":[35],"accuracy":[36],"are":[37,131,141],"critical":[38],"in":[39,97],"edge":[40],"scenarios.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,89],"build":[47],"Adaptive":[49],"Deep":[50],"Neural":[51],"Networks":[52],"(ADNNs)":[53],"employ":[55],"Multi-Armed":[57],"Bandit":[58],"(MAB)":[59],"framework.":[60],"Current":[61],"literature":[62],"leverages":[63],"first":[65,109],"version":[66],"Upper":[69,93],"Confidence":[70,94],"Bound":[71,95],"(UCB1)":[72],"strategy":[73],"to":[74,119],"select":[76],"optimal":[78],"confidence":[79],"threshold,":[80],"enabling":[81],"efficient":[82],"early":[83],"exits":[84],"without":[85],"sacrificing":[86],"accuracy.":[87],"However,":[88],"introduce":[90],"four":[91],"additional":[92],"ADNNs,":[98],"namely":[99],"UCB-V,":[100],"UCB-Tuned,":[101],"UCB-Bayes,":[102],"UCB-BwK,":[104],"perform,":[106],"for":[107],"time,":[110],"comparative":[112],"study":[113],"these":[115],"respect":[118],"trade-offs":[120],"between":[121],"accuracy,":[122],"consumption,":[124],"latency.":[126],"The":[127,185],"proposed":[128],"UCB":[129],"employed":[132],"ResNet":[135],"MobileViT":[137],"networks,":[139],"evaluated":[142],"benchmark":[145],"datasets":[146],"CIFAR-10,":[148],"CIFAR-10.1,":[149],"CIFAR-100.":[151],"Experimental":[152],"results":[153],"demonstrate":[154],"all":[156],"achieve":[158],"sub-linear":[159],"cumulative":[160],"regret,":[161],"UCB-Bayes":[163],"converging":[164],"fastest,":[166],"followed":[167],"by":[168],"UCB-Tuned":[169,175],"UCB-V.":[171],"Finally,":[172],"UCB-V":[173],"dominate":[176],"Pareto":[178],"Frontiers":[179],"accuracy-latency":[181],"accuracy-energy":[183],"trade-offs.":[184],"implementation":[186],"code":[187],"is":[188],"available":[189],"here:":[190],"https://github.com/gr3gor1/MAB_UCB":[191]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-30T00:00:00"}