{"id":"https://openalex.org/W7160274806","doi":"https://doi.org/10.1109/wacv61042.2026.00292","title":"Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning","display_name":"Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160274806","doi":"https://doi.org/10.1109/wacv61042.2026.00292"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043335223","display_name":"Arani Roy","orcid":"https://orcid.org/0000-0001-5826-3426"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arani Roy","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135392136","display_name":"Marco P. Apolinario","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco P. Apolinario","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134390653","display_name":"Shristi Das Biswas","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shristi Das Biswas","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135410023","display_name":"Kaushik Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Roy","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"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":"2984","last_page":"2992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.1265999972820282,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1265999972820282,"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":0.10019999742507935,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.08940000087022781,"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/recipe","display_name":"Recipe","score":0.6543999910354614},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3206000030040741},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.30090001225471497},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2962000072002411},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.29420000314712524},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2718000113964081}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.6543999910354614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6065999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4178999960422516},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2552737632","https://openalex.org/W2565565355","https://openalex.org/W2618530766","https://openalex.org/W2962998014","https://openalex.org/W3016391357","https://openalex.org/W3035646933","https://openalex.org/W3121174466","https://openalex.org/W3171259667","https://openalex.org/W4236362309","https://openalex.org/W4250589301","https://openalex.org/W7133199283"],"related_works":[],"abstract_inverted_index":{"Training":[0],"deep":[1],"neural":[2,52],"networks":[3],"(DNNs)":[4],"with":[5,34,89],"backpropagation":[6],"(BP)":[7],"achieves":[8,157],"state-of-the-art":[9],"accuracy":[10,158],"but":[11,38],"requires":[12],"global":[13],"error":[14],"propagation":[15],"and":[16,23,44,105,122,151,188],"full":[17],"parameterization,":[18],"leading":[19],"to":[20,92,112,134,160,191],"substantial":[21],"memory":[22,36],"computational":[24],"overhead.":[25],"Direct":[26],"Feedback":[27,108],"Alignment":[28],"(DFA)":[29],"enables":[30],"local,":[31],"parallelizable":[32],"updates":[33,90],"lower":[35],"requirements":[37],"is":[39,83],"limited":[40],"by":[41,72],"unstructured":[42],"feedback":[43,123],"poor":[45],"scalability":[46],"in":[47,85,173],"deeper":[48],"architectures,":[49],"specially":[50],"convolutional":[51],"networks.":[53],"To":[54],"address":[55],"these":[56],"limitations,":[57],"we":[58],"propose":[59],"a":[60,97,186],"structured":[61],"local":[62,180],"learning":[63,181],"framework":[64],"that":[65,100,154,161],"operates":[66],"directly":[67],"on":[68,141,148,182],"low-rank":[69,175,183],"manifolds":[70,184],"defined":[71],"the":[73,93,114,128,135,167,174],"Singular":[74],"Value":[75],"Decomposition":[76],"(SVD)":[77],"of":[78,130,162,169],"weight":[79],"matrices.":[80],"Each":[81],"layer":[82],"trained":[84],"its":[86],"decomposed":[87],"form,":[88],"applied":[91],"SVD":[94,115],"components":[95],"using":[96],"composite":[98],"loss":[99,171],"integrates":[101],"cross-entropy,":[102],"subspace":[103],"alignment,":[104],"orthogonality":[106],"regularization.":[107],"matrices":[109],"are":[110],"constructed":[111],"match":[113],"structure,":[116],"ensuring":[117],"consistent":[118],"alignment":[119],"between":[120],"forward":[121],"pathways.":[124],"Our":[125],"method":[126,156],"reduces":[127],"number":[129],"trainable":[131],"parameters":[132],"relative":[133],"original":[136],"DFA":[137],"model,":[138],"without":[139],"relying":[140],"pruning":[142],"or":[143],"post":[144],"hoc":[145],"compression.":[146],"Experiments":[147],"CIFAR-10,":[149],"CIFAR-100,":[150],"ImageNet":[152],"show":[153],"our":[155],"comparable":[159],"BP.":[163],"Ablation":[164],"studies":[165],"confirm":[166],"importance":[168],"each":[170],"term":[172],"setting.":[176],"These":[177],"results":[178],"establish":[179],"as":[185],"principled":[187],"scalable":[189],"alternative":[190],"full-rank":[192],"gradient-based":[193],"training.":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}