{"id":"https://openalex.org/W2996086314","doi":null,"title":"Understanding l4-based Dictionary Learning: Interpretation, Stability, and Robustness","display_name":"Understanding l4-based Dictionary Learning: Interpretation, Stability, and Robustness","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2996086314","mag":"2996086314"},"language":"en","primary_location":{"id":"mag:2996086314","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/iclr/iclr2020.html#ZhaiMZ020","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5110816004","display_name":"Yuexiang Zhai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuexiang Zhai","raw_affiliation_strings":["University of California, Berkeley, Berkeley, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062615994","display_name":"Hermish Mehta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I71209653","display_name":"Bocconi University","ror":"https://ror.org/05crjpb27","country_code":"IT","type":"education","lineage":["https://openalex.org/I71209653"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Hermish Mehta","raw_affiliation_strings":["Bocconi University, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bocconi University, Milan, Italy","institution_ids":["https://openalex.org/I71209653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088606320","display_name":"Zhengyuan Zhou","orcid":"https://orcid.org/0000-0002-0005-9411","observed_orcids":["https://orcid.org/0000-0002-0005-9411"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengyuan Zhou","raw_affiliation_strings":["New York University, New York, United States"],"raw_orcid":"https://orcid.org/0000-0002-0005-9411","affiliations":[{"raw_affiliation_string":"New York University, New York, United States","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062841020","display_name":"Yi Ma","orcid":"https://orcid.org/0000-0001-5485-419X","observed_orcids":["https://orcid.org/0000-0001-5485-419X","https://orcid.org/0000-0003-1832-8920","https://orcid.org/0000-0002-6715-4309"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ma","raw_affiliation_strings":["University of California, Berkeley, Berkeley, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6611,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6572303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.003800000064074993,"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/T10057","display_name":"Face and Expression Recognition","score":0.000699999975040555,"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/dictionary-learning","display_name":"dictionary learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/sparse-coding","display_name":"sparse coding","score":0.7369999885559082},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"principal component analysis","score":0.8450000286102295},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"independent component analysis","score":1.0},{"id":"https://openalex.org/keywords/fixed-point-iteration","display_name":"fixed point iteration","score":0.8650000095367432},{"id":"https://openalex.org/keywords/outlier-robustness","display_name":"outlier robustness","score":0.8309999704360962},{"id":"https://openalex.org/keywords/sparse-corruptions","display_name":"sparse corruptions","score":0.7770000100135803},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.6990000009536743},{"id":"https://openalex.org/keywords/geometric-interpretation","display_name":"geometric interpretation","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7426993250846863},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6695269346237183},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.6326747536659241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6298101544380188},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5811951160430908},{"id":"https://openalex.org/C2988886741","wikidata":"https://www.wikidata.org/wiki/Q25304494","display_name":"Dictionary learning","level":3,"score":0.5289487838745117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5069983005523682},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5011265277862549},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4869304895401001},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4502444267272949},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.418050616979599},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4128724932670593},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4055880904197693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3016592860221863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2731650471687317},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24537715315818787},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.13347452878952026},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2996086314","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/iclr/iclr2020.html#ZhaiMZ020","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W104847522","https://openalex.org/W1989243075","https://openalex.org/W1991566301","https://openalex.org/W1993693225","https://openalex.org/W1995168330","https://openalex.org/W2008732654","https://openalex.org/W2019502123","https://openalex.org/W2053885701","https://openalex.org/W2065180801","https://openalex.org/W2078455576","https://openalex.org/W2082855665","https://openalex.org/W2097417531","https://openalex.org/W2098760944","https://openalex.org/W2105464873","https://openalex.org/W2106334384","https://openalex.org/W2108665656","https://openalex.org/W2112796928","https://openalex.org/W2114122776","https://openalex.org/W2118550318","https://openalex.org/W2120023453","https://openalex.org/W2121058967","https://openalex.org/W2123649031","https://openalex.org/W2129812935","https://openalex.org/W2145889472","https://openalex.org/W2145962650","https://openalex.org/W2153663612","https://openalex.org/W2163112044","https://openalex.org/W2346689370","https://openalex.org/W2538623560","https://openalex.org/W2892755733","https://openalex.org/W2898095198","https://openalex.org/W2906161608","https://openalex.org/W2963168706","https://openalex.org/W2963423870","https://openalex.org/W2963558956","https://openalex.org/W2963589422","https://openalex.org/W2963774180","https://openalex.org/W2972345688","https://openalex.org/W3023058184","https://openalex.org/W3086393698","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2948586274","https://openalex.org/W7213794263","https://openalex.org/W3091251352","https://openalex.org/W7055365508","https://openalex.org/W2630755204","https://openalex.org/W3028947111","https://openalex.org/W2398274324","https://openalex.org/W2552291579","https://openalex.org/W1989299554","https://openalex.org/W2579893265"],"abstract_inverted_index":{"Recently":[0],"$\\ell^4$-norm":[1],"maximization":[2],"has":[3,25],"been":[4],"proposed":[5,22],"to":[6,27,36,103,109,113],"solve":[7],"the":[8,49,91,96,128],"sparse":[9,100,114],"dictionary":[10],"learning":[11],"(SDL)":[12],"problem.":[13],"The":[14],"simple":[15],"MSP":[16,97],"(matching,":[17],"stretching,":[18],"and":[19,31,45,52,111,135,143],"projection)":[20],"algorithm":[21,40,98],"by":[23],"\\cite{zhai2019a}":[24],"shown":[26],"be":[28],"surprisingly":[29],"efficient":[30],"effective.":[32],"This":[33],"paper":[34],"aims":[35],"better":[37],"understand":[38],"this":[39],"from":[41],"its":[42],"strong":[43],"geometric":[44],"statistical":[46,119],"connections":[47,63],"with":[48,139],"classic":[50],"PCA":[51],"ICA,":[53],"as":[54,56],"well":[55],"their":[57],"associated":[58],"fixed-point":[59],"style":[60],"algorithms.":[61],"Such":[62],"provide":[64,117,133],"a":[65],"unified":[66],"way":[67],"of":[68,81,90],"viewing":[69],"problems":[70],"that":[71],"pursue":[72],"{\\em":[73,75,78],"principal},":[74],"independent},":[76],"or":[77],"sparse}":[79],"components":[80],"high-dimensional":[82],"data.":[83],"Our":[84],"studies":[85],"reveal":[86],"additional":[87],"good":[88],"properties":[89],"$\\ell^4$-maximization:":[92],"not":[93],"only":[94],"is":[95],"for":[99,121],"coding":[101],"insensitive":[102],"small":[104],"noise,":[105],"but":[106],"also":[107,132],"robust":[108],"outliers,":[110],"resilient":[112],"corruptions.":[115],"We":[116],"preliminary":[118],"justification":[120],"such":[122],"inherently":[123],"nice":[124],"properties.":[125],"To":[126],"corroborate":[127],"theoretical":[129],"analysis,":[130],"we":[131],"extensive":[134],"compelling":[136],"experimental":[137],"evidence":[138],"both":[140],"synthetic":[141],"data":[142],"real":[144],"images.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-26T00:00:00"}