{"id":"https://openalex.org/W3138316003","doi":"https://doi.org/10.1109/bigdata50022.2020.9378236","title":"Hyper-parameter optimization with REINFORCE and Masked Attention Auto-regressive Density Estimators","display_name":"Hyper-parameter optimization with REINFORCE and Masked Attention Auto-regressive Density Estimators","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3138316003","doi":"https://doi.org/10.1109/bigdata50022.2020.9378236","mag":"3138316003"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","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/A5010869465","display_name":"Chepuri Shri Krishna","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chepuri Shri Krishna","raw_affiliation_strings":["Walmart Global Tech India,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech India,Bengaluru,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038130624","display_name":"Ashish Gupta","orcid":"https://orcid.org/0000-0002-1424-1361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Gupta","raw_affiliation_strings":["Walmart Global Tech India,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech India,Bengaluru,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110751012","display_name":"Swarnim Narayan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swarnim Narayan","raw_affiliation_strings":["Walmart Global Tech India,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech India,Bengaluru,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084346046","display_name":"Himanshu Rai","orcid":"https://orcid.org/0000-0003-4768-3817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Himanshu Rai","raw_affiliation_strings":["Walmart Global Tech India,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech India,Bengaluru,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038014794","display_name":"Diksha Manchanda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diksha Manchanda","raw_affiliation_strings":["Walmart Global Tech India,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech India,Bengaluru,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010869465"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18784029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"5108","last_page":"5117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7153494358062744},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6500820517539978},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6375827789306641},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5318863987922668},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5229873657226562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4901807904243469},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4881158769130707},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.471934050321579},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46824967861175537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11510118842124939},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11381343007087708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153494358062744},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6500820517539978},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6375827789306641},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5318863987922668},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5229873657226562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4901807904243469},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4881158769130707},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.471934050321579},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46824967861175537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11510118842124939},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11381343007087708},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":123,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1191599655","https://openalex.org/W1437335841","https://openalex.org/W1522301498","https://openalex.org/W1746819321","https://openalex.org/W1815076433","https://openalex.org/W1866230956","https://openalex.org/W1868018859","https://openalex.org/W1938755728","https://openalex.org/W2064675550","https://openalex.org/W2097998348","https://openalex.org/W2099471712","https://openalex.org/W2102539288","https://openalex.org/W2106411961","https://openalex.org/W2119717200","https://openalex.org/W2131241448","https://openalex.org/W2133564696","https://openalex.org/W2156737235","https://openalex.org/W2170612786","https://openalex.org/W2319278070","https://openalex.org/W2519091744","https://openalex.org/W2553303224","https://openalex.org/W2594529350","https://openalex.org/W2616602896","https://openalex.org/W2736601468","https://openalex.org/W2782417188","https://openalex.org/W2788853733","https://openalex.org/W2796265726","https://openalex.org/W2803461142","https://openalex.org/W2810075754","https://openalex.org/W2885311373","https://openalex.org/W2888429796","https://openalex.org/W2916118939","https://openalex.org/W2917028965","https://openalex.org/W2942415903","https://openalex.org/W2949264490","https://openalex.org/W2949382160","https://openalex.org/W2951104886","https://openalex.org/W2951245151","https://openalex.org/W2951559648","https://openalex.org/W2951886768","https://openalex.org/W2952838738","https://openalex.org/W2953318193","https://openalex.org/W2962746461","https://openalex.org/W2962750597","https://openalex.org/W2962990490","https://openalex.org/W2963233958","https://openalex.org/W2963403868","https://openalex.org/W2963423218","https://openalex.org/W2963428348","https://openalex.org/W2963521729","https://openalex.org/W2963748792","https://openalex.org/W2963778169","https://openalex.org/W2963821229","https://openalex.org/W2963873275","https://openalex.org/W2964043796","https://openalex.org/W2964081807","https://openalex.org/W2964121744","https://openalex.org/W2964122153","https://openalex.org/W2964212578","https://openalex.org/W2964259004","https://openalex.org/W2964308564","https://openalex.org/W2964515685","https://openalex.org/W2965658867","https://openalex.org/W2970597249","https://openalex.org/W2972268045","https://openalex.org/W2973943791","https://openalex.org/W2981406437","https://openalex.org/W2981748264","https://openalex.org/W2996012599","https://openalex.org/W2996409713","https://openalex.org/W3007501395","https://openalex.org/W4211049957","https://openalex.org/W4255158661","https://openalex.org/W4289763996","https://openalex.org/W4293407536","https://openalex.org/W4295185264","https://openalex.org/W4300427683","https://openalex.org/W4300687381","https://openalex.org/W4320005659","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6607333740","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6639317949","https://openalex.org/W6639506587","https://openalex.org/W6674385629","https://openalex.org/W6676179485","https://openalex.org/W6678911119","https://openalex.org/W6679434410","https://openalex.org/W6683195989","https://openalex.org/W6684642658","https://openalex.org/W6692846177","https://openalex.org/W6706363465","https://openalex.org/W6729956949","https://openalex.org/W6729972426","https://openalex.org/W6732492507","https://openalex.org/W6734593296","https://openalex.org/W6738227506","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6741459021","https://openalex.org/W6745614327","https://openalex.org/W6746090280","https://openalex.org/W6747491877","https://openalex.org/W6748057086","https://openalex.org/W6748587240","https://openalex.org/W6751209437","https://openalex.org/W6751421292","https://openalex.org/W6751455638","https://openalex.org/W6752515464","https://openalex.org/W6753278433","https://openalex.org/W6753701838","https://openalex.org/W6756887525","https://openalex.org/W6759402996","https://openalex.org/W6759828284","https://openalex.org/W6763701032","https://openalex.org/W6767472356","https://openalex.org/W6767953722","https://openalex.org/W6769661145","https://openalex.org/W6771784742"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"has":[2],"yielded":[3],"promising":[4],"results":[5],"for":[6,66,142],"Neural":[7],"Architecture":[8],"Search":[9,180],"(NAS).":[10],"In":[11,146],"this":[12,55,170],"paper,":[13],"we":[14],"demonstrate":[15,79],"how":[16,80],"its":[17],"performance":[18,83],"can":[19,84],"be":[20,85],"improved":[21,87],"by":[22,88],"using":[23,90,166],"a":[24,37,113,124,139,173],"simplified":[25,34],"Transformer":[26,35,104],"block":[27,110],"to":[28,41,157,196],"model":[29,42,59,158,187],"the":[30,81,159,163],"policy":[31,99,160],"network.":[32],"The":[33],"uses":[36],"2-stream":[38],"attention-based":[39,167],"mechanism":[40],"hyper-parameter":[43,128],"dependencies":[44],"while":[45,204],"avoiding":[46],"layer":[47],"normalization":[48],"and":[49,101,126,201,207],"position":[50],"encoding.":[51],"We":[52,78,193],"posit":[53],"that":[54,153],"parsimonious":[56],"design":[57],"balances":[58],"complexity":[60],"against":[61],"expressiveness,":[62],"making":[63],"it":[64,132,148,177],"suitable":[65],"discovering":[67,182],"optimal":[68],"architectures":[69,156,188],"in":[70,169,181,199],"high-dimensional":[71],"search":[72],"spaces":[73],"with":[74,106],"limited":[75],"exploration":[76],"budgets.":[77],"algorithm's":[82],"further":[86],"a)":[89],"an":[91],"actor-critic":[92],"style":[93],"algorithm":[94,119],"instead":[95],"of":[96,165],"plain":[97],"vanilla":[98],"gradient":[100],"b)":[102],"ensembling":[103],"blocks":[105],"shared":[107],"parameters,":[108],"each":[109],"conditioned":[111],"on":[112,136],"different":[114],"auto-regressive":[115],"factorization":[116],"order.":[117],"Our":[118],"works":[120],"well":[121],"as":[122],"both":[123],"NAS":[125,144],"generic":[127,174],"optimization":[129],"(HPO)":[130],"algorithm:":[131],"outperformed":[133,149,178],"most":[134],"algorithms":[135],"NAS-Bench-101":[137],"[1],":[138],"public":[140],"data-set":[141],"benchmarking":[143],"algorithms.":[145],"particular,":[147],"RL":[150],"based":[151],"methods":[152],"use":[154],"alternate":[155],"network,":[161],"underlining":[162],"value":[164],"networks":[168],"setting.":[171],"As":[172],"HPO":[175],"algorithm,":[176],"Random":[179],"more":[183],"accurate":[184],"multi-layer":[185],"perceptron":[186],"across":[189],"2":[190],"regression":[191],"tasks.":[192],"have":[194],"adhered":[195],"guidelines":[197],"listed":[198],"Lindauer":[200],"Hutter":[202],"[2]":[203],"designing":[205],"experiments":[206],"reporting":[208],"results.":[209]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}