{"id":"https://openalex.org/W7154202963","doi":"https://doi.org/10.48550/arxiv.2604.10374","title":"Probabilistic Gradient Coding via Structure-Preserving Sparsification","display_name":"Probabilistic Gradient Coding via Structure-Preserving Sparsification","publication_year":2026,"publication_date":"2026-04-11","ids":{"openalex":"https://openalex.org/W7154202963","doi":"https://doi.org/10.48550/arxiv.2604.10374"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.10374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.10374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133552603","display_name":"Yuxin Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133607047","display_name":"Wenqin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122997983","display_name":"Lele Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lele","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9729999899864197,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9729999899864197,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.007499999832361937,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.006599999964237213,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6412000060081482},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4390999972820282},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4129999876022339},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4099999964237213},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.3917999863624573},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.36739999055862427},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6412000060081482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5224999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48919999599456787},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4390999972820282},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4129999876022339},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C64812099","wikidata":"https://www.wikidata.org/wiki/Q176604","display_name":"Random matrix","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C67692717","wikidata":"https://www.wikidata.org/wiki/Q187444","display_name":"Low-density parity-check code","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C177384507","wikidata":"https://www.wikidata.org/wiki/Q1149000","display_name":"Multivariate normal distribution","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.10374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.10374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Gradient":[0],"coding":[1],"is":[2,70],"a":[3,33,122,128,146,192],"distributed":[4,224],"computing":[5,15,27,225],"technique":[6],"aiming":[7],"to":[8,183],"provide":[9],"robustness":[10,48],"against":[11],"slow":[12],"or":[13],"non-responsive":[14],"nodes,":[16],"known":[17],"as":[18],"stragglers,":[19],"while":[20,110,156],"balancing":[21],"the":[22,44,53,59,87,94,102,105,111,157,186,195,203],"computational":[23,50],"load":[24,51],"for":[25,64,222],"responsive":[26],"nodes.":[28],"Among":[29],"existing":[30],"gradient":[31,41,67,84,91,97,139,159,188,214],"codes,":[32,85,215],"construction":[34],"based":[35,120],"on":[36,121],"combinatorial":[37,106],"designs,":[38],"called":[39],"BIBD":[40,66,187,210,213],"code,":[42],"achieves":[43],"best":[45],"trade-off":[46],"between":[47],"and":[49,93,131,211,218],"in":[52],"worst-case":[54,179],"adversarial":[55],"straggler":[56],"setting.":[57],"However,":[58],"range":[60,205],"of":[61,108,185,206],"system":[62,207],"parameters":[63,197,208],"which":[65],"codes":[68,118,177],"exist":[69],"limited.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"overcome":[76],"these":[77],"limitations":[78],"by":[79,152],"proposing":[80],"two":[81],"new":[82],"probabilistic":[83,100],"termed":[86],"\\emph{Sparse":[88],"Gaussian}":[89],"(SG)":[90],"code":[92,140,160,189,193],"\\emph{Expansion-Preserving}":[95],"(EP)":[96],"code.":[98],"Through":[99],"constructions,":[101],"former":[103],"preserves":[104,113],"structure":[107],"BIBDs,":[109],"latter":[112],"key":[114,172],"spectral":[115,173],"properties.":[116,174],"Both":[117],"are":[119],"common":[123],"two-step":[124],"framework:":[125],"first":[126],"generating":[127],"random":[129,154],"matrix":[130,144,164],"then":[132],"applying":[133],"distinct":[134],"sparsification":[135],"procedures.":[136],"The":[137],"SG":[138],"constructs":[141],"its":[142,162],"encoding":[143,163],"from":[145,165],"correlated":[147],"multivariate":[148],"Gaussian":[149],"distribution":[150],"masked":[151],"Bernoulli":[153],"variables,":[155],"EP":[158],"derives":[161],"sparsified":[166],"expander-like":[167],"graph":[168],"structures":[169],"that":[170,184],"preserve":[171],"Experimentally,":[175],"both":[176],"achieve":[178],"error":[180],"performance":[181],"comparable":[182],"(when":[190],"such":[191],"with":[194],"same":[196],"exists).":[198],"Moreover,":[199],"they":[200],"substantially":[201],"extend":[202],"feasible":[204],"beyond":[209],"soft":[212],"offering":[216],"practical":[217],"theoretically":[219],"grounded":[220],"solutions":[221],"large-scale":[223],"tasks.":[226]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-15T00:00:00"}