Federated Learning's Blessing: FedAvg has Linear Speedup Article Swipe
Zhaonan Qu
,
Kaixiang Lin
,
Zhaojian Li
,
Jiayu Zhou
,
Zhengyuan Zhou
·
YOU?
·
· 2021
· Open Access
·
YOU?
·
· 2021
· Open Access
·
Federated learning (FL) learns a model jointly from a set of participating devices without sharing each other's privately held data. The characteristics of non-\textit{i.i.d.} data across the network, low device participation, high communication costs, and the mandate that data remain private bring challenges in understanding the convergence of FL algorithms, particularly in regards to how convergence scales with the number of participating devices. In this paper, we focus on Federated Averaging (FedAvg)--arguably the most popular and effective FL algorithm class in use today--and provide a unified and comprehensive study of its convergence rate. Although FedAvg has recently been studied by an emerging line of literature, it remains open as to how FedAvg's convergence scales with the number of participating devices in the fully heterogeneous FL setting--a crucial question whose answer would shed light on the performance of FedAvg in large FL systems. We fill this gap by providing a unified analysis that establishes convergence guarantees for FedAvg under three classes of problems: strongly convex smooth, convex smooth, and overparameterized strongly convex smooth problems. We show that FedAvg enjoys linear speedup in each case, although with different convergence rates and communication efficiencies. While there have been linear speedup results from distributed optimization that assumes full participation, ours are the first to establish linear speedup for FedAvg under both statistical and system heterogeneity. For strongly convex and convex problems, we also characterize the corresponding convergence rates for the Nesterov accelerated FedAvg algorithm, which are the first linear speedup guarantees for momentum variants of FedAvg in the convex setting. To provably accelerate FedAvg, we design a new momentum-based FL algorithm that further improves the convergence rate in overparameterized linear regression problems. Empirical studies of the algorithms in various settings have supported our theoretical results.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://arxiv.org/pdf/2007.05690.pdf
- OA Status
- green
- Cited By
- 22
- References
- 41
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3041733661
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3041733661Canonical identifier for this work in OpenAlex
- Title
-
Federated Learning's Blessing: FedAvg has Linear SpeedupWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-05-04Full publication date if available
- Authors
-
Zhaonan Qu, Kaixiang Lin, Zhaojian Li, Jiayu Zhou, Zhengyuan ZhouList of authors in order
- Landing page
-
https://arxiv.org/pdf/2007.05690.pdfPublisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2007.05690.pdfDirect OA link when available
- Concepts
-
Speedup, Computer science, Convergence (economics), Rate of convergence, Convex function, Algorithm, Regular polygon, Theoretical computer science, Parallel computing, Mathematics, Telecommunications, Economics, Geometry, Economic growth, Channel (broadcasting)Top concepts (fields/topics) attached by OpenAlex
- Cited by
-
22Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 7, 2023: 7, 2022: 2, 2021: 4, 2020: 2Per-year citation counts (last 5 years)
- References (count)
-
41Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3041733661 |
|---|---|
| doi | |
| ids.mag | 3041733661 |
| ids.openalex | https://openalex.org/W3041733661 |
| fwci | |
| type | preprint |
| title | Federated Learning's Blessing: FedAvg has Linear Speedup |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10764 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 1.0 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Privacy-Preserving Technologies in Data |
| topics[1].id | https://openalex.org/T11612 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9983999729156494 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Stochastic Gradient Optimization Techniques |
| topics[2].id | https://openalex.org/T11704 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9860000014305115 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1706 |
| topics[2].subfield.display_name | Computer Science Applications |
| topics[2].display_name | Mobile Crowdsensing and Crowdsourcing |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C68339613 |
| concepts[0].level | 2 |
| concepts[0].score | 0.970496416091919 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1549489 |
| concepts[0].display_name | Speedup |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6934459805488586 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2777303404 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6861423254013062 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q759757 |
| concepts[2].display_name | Convergence (economics) |
| concepts[3].id | https://openalex.org/C57869625 |
| concepts[3].level | 3 |
| concepts[3].score | 0.5661230087280273 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1783502 |
| concepts[3].display_name | Rate of convergence |
| concepts[4].id | https://openalex.org/C145446738 |
| concepts[4].level | 3 |
| concepts[4].score | 0.451604962348938 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q319913 |
| concepts[4].display_name | Convex function |
| concepts[5].id | https://openalex.org/C11413529 |
| concepts[5].level | 1 |
| concepts[5].score | 0.40923580527305603 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[5].display_name | Algorithm |
| concepts[6].id | https://openalex.org/C112680207 |
| concepts[6].level | 2 |
| concepts[6].score | 0.3728351593017578 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q714886 |
| concepts[6].display_name | Regular polygon |
| concepts[7].id | https://openalex.org/C80444323 |
| concepts[7].level | 1 |
| concepts[7].score | 0.32543283700942993 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[7].display_name | Theoretical computer science |
| concepts[8].id | https://openalex.org/C173608175 |
| concepts[8].level | 1 |
| concepts[8].score | 0.2723158597946167 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[8].display_name | Parallel computing |
| concepts[9].id | https://openalex.org/C33923547 |
| concepts[9].level | 0 |
| concepts[9].score | 0.20572736859321594 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[9].display_name | Mathematics |
| concepts[10].id | https://openalex.org/C76155785 |
| concepts[10].level | 1 |
| concepts[10].score | 0.17651128768920898 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[10].display_name | Telecommunications |
| concepts[11].id | https://openalex.org/C162324750 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[11].display_name | Economics |
| concepts[12].id | https://openalex.org/C2524010 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[12].display_name | Geometry |
| concepts[13].id | https://openalex.org/C50522688 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q189833 |
| concepts[13].display_name | Economic growth |
| concepts[14].id | https://openalex.org/C127162648 |
| concepts[14].level | 2 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q16858953 |
| concepts[14].display_name | Channel (broadcasting) |
| keywords[0].id | https://openalex.org/keywords/speedup |
| keywords[0].score | 0.970496416091919 |
| keywords[0].display_name | Speedup |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6934459805488586 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/convergence |
| keywords[2].score | 0.6861423254013062 |
| keywords[2].display_name | Convergence (economics) |
| keywords[3].id | https://openalex.org/keywords/rate-of-convergence |
| keywords[3].score | 0.5661230087280273 |
| keywords[3].display_name | Rate of convergence |
| keywords[4].id | https://openalex.org/keywords/convex-function |
| keywords[4].score | 0.451604962348938 |
| keywords[4].display_name | Convex function |
| keywords[5].id | https://openalex.org/keywords/algorithm |
| keywords[5].score | 0.40923580527305603 |
| keywords[5].display_name | Algorithm |
| keywords[6].id | https://openalex.org/keywords/regular-polygon |
| keywords[6].score | 0.3728351593017578 |
| keywords[6].display_name | Regular polygon |
| keywords[7].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[7].score | 0.32543283700942993 |
| keywords[7].display_name | Theoretical computer science |
| keywords[8].id | https://openalex.org/keywords/parallel-computing |
| keywords[8].score | 0.2723158597946167 |
| keywords[8].display_name | Parallel computing |
| keywords[9].id | https://openalex.org/keywords/mathematics |
| keywords[9].score | 0.20572736859321594 |
| keywords[9].display_name | Mathematics |
| keywords[10].id | https://openalex.org/keywords/telecommunications |
| keywords[10].score | 0.17651128768920898 |
| keywords[10].display_name | Telecommunications |
| language | en |
| locations[0].id | mag:3041733661 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | |
| locations[0].raw_source_name | arXiv (Cornell University) |
| locations[0].landing_page_url | https://arxiv.org/pdf/2007.05690.pdf |
| authorships[0].author.id | https://openalex.org/A5062138997 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1484-1217 |
| authorships[0].author.display_name | Zhaonan Qu |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I97018004 |
| authorships[0].affiliations[0].raw_affiliation_string | Stanford University () |
| authorships[0].institutions[0].id | https://openalex.org/I97018004 |
| authorships[0].institutions[0].ror | https://ror.org/00f54p054 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I97018004 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Stanford University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhaonan Qu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Stanford University () |
| authorships[1].author.id | https://openalex.org/A5100443077 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-8626-8934 |
| authorships[1].author.display_name | Kaixiang Lin |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I87216513 |
| authorships[1].affiliations[0].raw_affiliation_string | Michigan State University |
| authorships[1].institutions[0].id | https://openalex.org/I87216513 |
| authorships[1].institutions[0].ror | https://ror.org/05hs6h993 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I87216513 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Michigan State University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Kaixiang Lin |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Michigan State University |
| authorships[2].author.id | https://openalex.org/A5037274043 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-0189-8719 |
| authorships[2].author.display_name | Zhaojian Li |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I87216513 |
| authorships[2].affiliations[0].raw_affiliation_string | Michigan State University |
| authorships[2].institutions[0].id | https://openalex.org/I87216513 |
| authorships[2].institutions[0].ror | https://ror.org/05hs6h993 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I87216513 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Michigan State University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhaojian Li |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Michigan State University |
| authorships[3].author.id | https://openalex.org/A5047215778 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-4336-6777 |
| authorships[3].author.display_name | Jiayu Zhou |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I87216513 |
| authorships[3].affiliations[0].raw_affiliation_string | Michigan State University |
| authorships[3].institutions[0].id | https://openalex.org/I87216513 |
| authorships[3].institutions[0].ror | https://ror.org/05hs6h993 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I87216513 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Michigan State University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jiayu Zhou |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Michigan State University |
| authorships[4].author.id | https://openalex.org/A5088606320 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-0005-9411 |
| authorships[4].author.display_name | Zhengyuan Zhou |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I57206974 |
| authorships[4].affiliations[0].raw_affiliation_string | New York University** |
| authorships[4].institutions[0].id | https://openalex.org/I57206974 |
| authorships[4].institutions[0].ror | https://ror.org/0190ak572 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I57206974 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | New York University |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Zhengyuan Zhou |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | New York University** |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2007.05690.pdf |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Federated Learning's Blessing: FedAvg has Linear Speedup |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-10-10T17:16:08.811792 |
| primary_topic.id | https://openalex.org/T10764 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 1.0 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Privacy-Preserving Technologies in Data |
| related_works | https://openalex.org/W2541884796, https://openalex.org/W2535838896, https://openalex.org/W3152624284, https://openalex.org/W2995022099, https://openalex.org/W3197361836, https://openalex.org/W3028382483, https://openalex.org/W3158169529, https://openalex.org/W3126879498, https://openalex.org/W3133883699, https://openalex.org/W3014598661, https://openalex.org/W3181588811, https://openalex.org/W3130057558, https://openalex.org/W2805942448, https://openalex.org/W2092577148, https://openalex.org/W2767441931, https://openalex.org/W2805631327, https://openalex.org/W3132163419, https://openalex.org/W2953041362, https://openalex.org/W2982154564, https://openalex.org/W2972428370 |
| cited_by_count | 22 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 7 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 7 |
| counts_by_year[2].year | 2022 |
| counts_by_year[2].cited_by_count | 2 |
| counts_by_year[3].year | 2021 |
| counts_by_year[3].cited_by_count | 4 |
| counts_by_year[4].year | 2020 |
| counts_by_year[4].cited_by_count | 2 |
| locations_count | 1 |
| best_oa_location.id | mag:3041733661 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | arXiv (Cornell University) |
| best_oa_location.landing_page_url | https://arxiv.org/pdf/2007.05690.pdf |
| primary_location.id | mag:3041733661 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | arXiv (Cornell University) |
| primary_location.landing_page_url | https://arxiv.org/pdf/2007.05690.pdf |
| publication_date | 2021-05-04 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2608239888, https://openalex.org/W2048305372, https://openalex.org/W3005503558, https://openalex.org/W2900120080, https://openalex.org/W2888679364, https://openalex.org/W3007345209, https://openalex.org/W2994635124, https://openalex.org/W3102816259, https://openalex.org/W2804978897, https://openalex.org/W3037674069, https://openalex.org/W2888561381, https://openalex.org/W2899748887, https://openalex.org/W2156779765, https://openalex.org/W2162287622, https://openalex.org/W3012576858, https://openalex.org/W2788629937, https://openalex.org/W2787738298, https://openalex.org/W2982654255, https://openalex.org/W2963179579, https://openalex.org/W2989808997, https://openalex.org/W3038022836, https://openalex.org/W2900182564, https://openalex.org/W2419597278, https://openalex.org/W2891735383, https://openalex.org/W1512098439, https://openalex.org/W2963318081, https://openalex.org/W2994684563, https://openalex.org/W2541884796, https://openalex.org/W2972497108, https://openalex.org/W2995022099, https://openalex.org/W1916951228, https://openalex.org/W3007279825, https://openalex.org/W3135166055, https://openalex.org/W2950220847, https://openalex.org/W2962795635, https://openalex.org/W2962712496, https://openalex.org/W2540893630, https://openalex.org/W2944542720, https://openalex.org/W2996442797, https://openalex.org/W2995653155, https://openalex.org/W2963300197 |
| referenced_works_count | 41 |
| abstract_inverted_index.a | 4, 8, 84, 148, 262 |
| abstract_inverted_index.FL | 48, 77, 124, 140, 265 |
| abstract_inverted_index.In | 63 |
| abstract_inverted_index.To | 256 |
| abstract_inverted_index.We | 142, 173 |
| abstract_inverted_index.an | 100 |
| abstract_inverted_index.as | 108 |
| abstract_inverted_index.by | 99, 146 |
| abstract_inverted_index.in | 43, 51, 80, 120, 138, 180, 252, 273, 283 |
| abstract_inverted_index.it | 105 |
| abstract_inverted_index.of | 10, 22, 47, 60, 89, 103, 117, 136, 160, 250, 280 |
| abstract_inverted_index.on | 68, 133 |
| abstract_inverted_index.to | 53, 109, 209 |
| abstract_inverted_index.we | 66, 227, 260 |
| abstract_inverted_index.For | 221 |
| abstract_inverted_index.The | 20 |
| abstract_inverted_index.and | 34, 75, 86, 167, 188, 218, 224 |
| abstract_inverted_index.are | 206, 241 |
| abstract_inverted_index.for | 155, 213, 234, 247 |
| abstract_inverted_index.gap | 145 |
| abstract_inverted_index.has | 95 |
| abstract_inverted_index.how | 54, 110 |
| abstract_inverted_index.its | 90 |
| abstract_inverted_index.low | 28 |
| abstract_inverted_index.new | 263 |
| abstract_inverted_index.our | 288 |
| abstract_inverted_index.set | 9 |
| abstract_inverted_index.the | 26, 35, 45, 58, 72, 115, 121, 134, 207, 230, 235, 242, 253, 270, 281 |
| abstract_inverted_index.use | 81 |
| abstract_inverted_index.(FL) | 2 |
| abstract_inverted_index.also | 228 |
| abstract_inverted_index.been | 97, 194 |
| abstract_inverted_index.both | 216 |
| abstract_inverted_index.data | 24, 38 |
| abstract_inverted_index.each | 15, 181 |
| abstract_inverted_index.fill | 143 |
| abstract_inverted_index.from | 7, 198 |
| abstract_inverted_index.full | 203 |
| abstract_inverted_index.have | 193, 286 |
| abstract_inverted_index.held | 18 |
| abstract_inverted_index.high | 31 |
| abstract_inverted_index.line | 102 |
| abstract_inverted_index.most | 73 |
| abstract_inverted_index.open | 107 |
| abstract_inverted_index.ours | 205 |
| abstract_inverted_index.rate | 272 |
| abstract_inverted_index.shed | 131 |
| abstract_inverted_index.show | 174 |
| abstract_inverted_index.that | 37, 151, 175, 201, 267 |
| abstract_inverted_index.this | 64, 144 |
| abstract_inverted_index.with | 57, 114, 184 |
| abstract_inverted_index.While | 191 |
| abstract_inverted_index.bring | 41 |
| abstract_inverted_index.case, | 182 |
| abstract_inverted_index.class | 79 |
| abstract_inverted_index.data. | 19 |
| abstract_inverted_index.first | 208, 243 |
| abstract_inverted_index.focus | 67 |
| abstract_inverted_index.fully | 122 |
| abstract_inverted_index.large | 139 |
| abstract_inverted_index.light | 132 |
| abstract_inverted_index.model | 5 |
| abstract_inverted_index.rate. | 92 |
| abstract_inverted_index.rates | 187, 233 |
| abstract_inverted_index.study | 88 |
| abstract_inverted_index.there | 192 |
| abstract_inverted_index.three | 158 |
| abstract_inverted_index.under | 157, 215 |
| abstract_inverted_index.which | 240 |
| abstract_inverted_index.whose | 128 |
| abstract_inverted_index.would | 130 |
| abstract_inverted_index.FedAvg | 94, 137, 156, 176, 214, 238, 251 |
| abstract_inverted_index.across | 25 |
| abstract_inverted_index.answer | 129 |
| abstract_inverted_index.convex | 163, 165, 170, 223, 225, 254 |
| abstract_inverted_index.costs, | 33 |
| abstract_inverted_index.design | 261 |
| abstract_inverted_index.device | 29 |
| abstract_inverted_index.enjoys | 177 |
| abstract_inverted_index.learns | 3 |
| abstract_inverted_index.linear | 178, 195, 211, 244, 275 |
| abstract_inverted_index.number | 59, 116 |
| abstract_inverted_index.paper, | 65 |
| abstract_inverted_index.remain | 39 |
| abstract_inverted_index.scales | 56, 113 |
| abstract_inverted_index.smooth | 171 |
| abstract_inverted_index.system | 219 |
| abstract_inverted_index.FedAvg, | 259 |
| abstract_inverted_index.assumes | 202 |
| abstract_inverted_index.classes | 159 |
| abstract_inverted_index.crucial | 126 |
| abstract_inverted_index.devices | 12, 119 |
| abstract_inverted_index.further | 268 |
| abstract_inverted_index.jointly | 6 |
| abstract_inverted_index.mandate | 36 |
| abstract_inverted_index.other's | 16 |
| abstract_inverted_index.popular | 74 |
| abstract_inverted_index.private | 40 |
| abstract_inverted_index.provide | 83 |
| abstract_inverted_index.regards | 52 |
| abstract_inverted_index.remains | 106 |
| abstract_inverted_index.results | 197 |
| abstract_inverted_index.sharing | 14 |
| abstract_inverted_index.smooth, | 164, 166 |
| abstract_inverted_index.speedup | 179, 196, 212, 245 |
| abstract_inverted_index.studied | 98 |
| abstract_inverted_index.studies | 279 |
| abstract_inverted_index.unified | 85, 149 |
| abstract_inverted_index.various | 284 |
| abstract_inverted_index.without | 13 |
| abstract_inverted_index.Although | 93 |
| abstract_inverted_index.FedAvg's | 111 |
| abstract_inverted_index.Nesterov | 236 |
| abstract_inverted_index.although | 183 |
| abstract_inverted_index.analysis | 150 |
| abstract_inverted_index.devices. | 62 |
| abstract_inverted_index.emerging | 101 |
| abstract_inverted_index.improves | 269 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.momentum | 248 |
| abstract_inverted_index.network, | 27 |
| abstract_inverted_index.provably | 257 |
| abstract_inverted_index.question | 127 |
| abstract_inverted_index.recently | 96 |
| abstract_inverted_index.results. | 290 |
| abstract_inverted_index.setting. | 255 |
| abstract_inverted_index.settings | 285 |
| abstract_inverted_index.strongly | 162, 169, 222 |
| abstract_inverted_index.systems. | 141 |
| abstract_inverted_index.variants | 249 |
| abstract_inverted_index.Averaging | 70 |
| abstract_inverted_index.Empirical | 278 |
| abstract_inverted_index.Federated | 0, 69 |
| abstract_inverted_index.algorithm | 78, 266 |
| abstract_inverted_index.different | 185 |
| abstract_inverted_index.effective | 76 |
| abstract_inverted_index.establish | 210 |
| abstract_inverted_index.privately | 17 |
| abstract_inverted_index.problems, | 226 |
| abstract_inverted_index.problems. | 172, 277 |
| abstract_inverted_index.problems: | 161 |
| abstract_inverted_index.providing | 147 |
| abstract_inverted_index.supported | 287 |
| abstract_inverted_index.accelerate | 258 |
| abstract_inverted_index.algorithm, | 239 |
| abstract_inverted_index.algorithms | 282 |
| abstract_inverted_index.challenges | 42 |
| abstract_inverted_index.guarantees | 154, 246 |
| abstract_inverted_index.regression | 276 |
| abstract_inverted_index.setting--a | 125 |
| abstract_inverted_index.today--and | 82 |
| abstract_inverted_index.accelerated | 237 |
| abstract_inverted_index.algorithms, | 49 |
| abstract_inverted_index.convergence | 46, 55, 91, 112, 153, 186, 232, 271 |
| abstract_inverted_index.distributed | 199 |
| abstract_inverted_index.establishes | 152 |
| abstract_inverted_index.literature, | 104 |
| abstract_inverted_index.performance | 135 |
| abstract_inverted_index.statistical | 217 |
| abstract_inverted_index.theoretical | 289 |
| abstract_inverted_index.characterize | 229 |
| abstract_inverted_index.optimization | 200 |
| abstract_inverted_index.particularly | 50 |
| abstract_inverted_index.communication | 32, 189 |
| abstract_inverted_index.comprehensive | 87 |
| abstract_inverted_index.corresponding | 231 |
| abstract_inverted_index.efficiencies. | 190 |
| abstract_inverted_index.heterogeneous | 123 |
| abstract_inverted_index.participating | 11, 61, 118 |
| abstract_inverted_index.understanding | 44 |
| abstract_inverted_index.heterogeneity. | 220 |
| abstract_inverted_index.momentum-based | 264 |
| abstract_inverted_index.participation, | 30, 204 |
| abstract_inverted_index.characteristics | 21 |
| abstract_inverted_index.overparameterized | 168, 274 |
| abstract_inverted_index.(FedAvg)--arguably | 71 |
| abstract_inverted_index.non-\textit{i.i.d.} | 23 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/17 |
| sustainable_development_goals[0].score | 0.4300000071525574 |
| sustainable_development_goals[0].display_name | Partnerships for the goals |
| citation_normalized_percentile |