FedExP: Speeding Up Federated Averaging via Extrapolation Article Swipe
Divyansh Jhunjhunwala
,
Shiqiang Wang
,
Gauri Joshi
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2301.09604
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2301.09604
Federated Averaging (FedAvg) remains the most popular algorithm for Federated Learning (FL) optimization due to its simple implementation, stateless nature, and privacy guarantees combined with secure aggregation. Recent work has sought to generalize the vanilla averaging in FedAvg to a generalized gradient descent step by treating client updates as pseudo-gradients and using a server step size. While the use of a server step size has been shown to provide performance improvement theoretically, the practical benefit of the server step size has not been seen in most existing works. In this work, we present FedExP, a method to adaptively determine the server step size in FL based on dynamically varying pseudo-gradients throughout the FL process. We begin by considering the overparameterized convex regime, where we reveal an interesting similarity between FedAvg and the Projection Onto Convex Sets (POCS) algorithm. We then show how FedExP can be motivated as a novel extension to the extrapolation mechanism that is used to speed up POCS. Our theoretical analysis later also discusses the implications of FedExP in underparameterized and non-convex settings. Experimental results show that FedExP consistently converges faster than FedAvg and competing baselines on a range of realistic FL datasets.
Related Topics
Concepts
Extrapolation
Computer science
Gradient descent
Stateless protocol
Range (aeronautics)
Similarity (geometry)
Regular polygon
Process (computing)
Simple (philosophy)
Convergence (economics)
Algorithm
Extension (predicate logic)
Descent (aeronautics)
Server
Projection (relational algebra)
Data mining
Mathematics
Artificial intelligence
Image (mathematics)
Statistics
Computer network
Composite material
Economics
Epistemology
Economic growth
Materials science
Geometry
Artificial neural network
Philosophy
Operating system
Engineering
Aerospace engineering
Programming language
State (computer science)
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2301.09604
- https://arxiv.org/pdf/2301.09604
- OA Status
- green
- Cited By
- 8
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4317951255
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4317951255Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2301.09604Digital Object Identifier
- Title
-
FedExP: Speeding Up Federated Averaging via ExtrapolationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-01-23Full publication date if available
- Authors
-
Divyansh Jhunjhunwala, Shiqiang Wang, Gauri JoshiList of authors in order
- Landing page
-
https://arxiv.org/abs/2301.09604Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2301.09604Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2301.09604Direct OA link when available
- Concepts
-
Extrapolation, Computer science, Gradient descent, Stateless protocol, Range (aeronautics), Similarity (geometry), Regular polygon, Process (computing), Simple (philosophy), Convergence (economics), Algorithm, Extension (predicate logic), Descent (aeronautics), Server, Projection (relational algebra), Data mining, Mathematics, Artificial intelligence, Image (mathematics), Statistics, Computer network, Composite material, Economics, Epistemology, Economic growth, Materials science, Geometry, Artificial neural network, Philosophy, Operating system, Engineering, Aerospace engineering, Programming language, State (computer science)Top concepts (fields/topics) attached by OpenAlex
- Cited by
-
8Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2, 2024: 4, 2023: 2Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4317951255 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2301.09604 |
| ids.doi | https://doi.org/10.48550/arxiv.2301.09604 |
| ids.openalex | https://openalex.org/W4317951255 |
| fwci | |
| type | preprint |
| title | FedExP: Speeding Up Federated Averaging via Extrapolation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11612 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9994000196456909 |
| 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 | Stochastic Gradient Optimization Techniques |
| topics[1].id | https://openalex.org/T10764 |
| 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 | Privacy-Preserving Technologies in Data |
| topics[2].id | https://openalex.org/T10500 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9908000230789185 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2206 |
| topics[2].subfield.display_name | Computational Mechanics |
| topics[2].display_name | Sparse and Compressive Sensing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C132459708 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8228588104248047 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q744069 |
| concepts[0].display_name | Extrapolation |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7131764888763428 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C153258448 |
| concepts[2].level | 3 |
| concepts[2].score | 0.5854052901268005 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1199743 |
| concepts[2].display_name | Gradient descent |
| concepts[3].id | https://openalex.org/C103613024 |
| concepts[3].level | 3 |
| concepts[3].score | 0.5783516764640808 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q230924 |
| concepts[3].display_name | Stateless protocol |
| concepts[4].id | https://openalex.org/C204323151 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5169107913970947 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q905424 |
| concepts[4].display_name | Range (aeronautics) |
| concepts[5].id | https://openalex.org/C103278499 |
| concepts[5].level | 3 |
| concepts[5].score | 0.5155006051063538 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q254465 |
| concepts[5].display_name | Similarity (geometry) |
| concepts[6].id | https://openalex.org/C112680207 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5104607343673706 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q714886 |
| concepts[6].display_name | Regular polygon |
| concepts[7].id | https://openalex.org/C98045186 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4813709855079651 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[7].display_name | Process (computing) |
| concepts[8].id | https://openalex.org/C2780586882 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4795484244823456 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7520643 |
| concepts[8].display_name | Simple (philosophy) |
| concepts[9].id | https://openalex.org/C2777303404 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4760172963142395 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q759757 |
| concepts[9].display_name | Convergence (economics) |
| concepts[10].id | https://openalex.org/C11413529 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4675914943218231 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[10].display_name | Algorithm |
| concepts[11].id | https://openalex.org/C2778029271 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4655006527900696 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5421931 |
| concepts[11].display_name | Extension (predicate logic) |
| concepts[12].id | https://openalex.org/C2776637919 |
| concepts[12].level | 2 |
| concepts[12].score | 0.44710758328437805 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q624380 |
| concepts[12].display_name | Descent (aeronautics) |
| concepts[13].id | https://openalex.org/C93996380 |
| concepts[13].level | 2 |
| concepts[13].score | 0.43714290857315063 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q44127 |
| concepts[13].display_name | Server |
| concepts[14].id | https://openalex.org/C57493831 |
| concepts[14].level | 2 |
| concepts[14].score | 0.41466227173805237 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q3134666 |
| concepts[14].display_name | Projection (relational algebra) |
| concepts[15].id | https://openalex.org/C124101348 |
| concepts[15].level | 1 |
| concepts[15].score | 0.3345091938972473 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[15].display_name | Data mining |
| concepts[16].id | https://openalex.org/C33923547 |
| concepts[16].level | 0 |
| concepts[16].score | 0.2219662070274353 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[16].display_name | Mathematics |
| concepts[17].id | https://openalex.org/C154945302 |
| concepts[17].level | 1 |
| concepts[17].score | 0.19955188035964966 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[17].display_name | Artificial intelligence |
| concepts[18].id | https://openalex.org/C115961682 |
| concepts[18].level | 2 |
| concepts[18].score | 0.16729208827018738 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[18].display_name | Image (mathematics) |
| concepts[19].id | https://openalex.org/C105795698 |
| concepts[19].level | 1 |
| concepts[19].score | 0.13787740468978882 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[19].display_name | Statistics |
| concepts[20].id | https://openalex.org/C31258907 |
| concepts[20].level | 1 |
| concepts[20].score | 0.12465572357177734 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[20].display_name | Computer network |
| concepts[21].id | https://openalex.org/C159985019 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q181790 |
| concepts[21].display_name | Composite material |
| concepts[22].id | https://openalex.org/C162324750 |
| concepts[22].level | 0 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[22].display_name | Economics |
| concepts[23].id | https://openalex.org/C111472728 |
| concepts[23].level | 1 |
| concepts[23].score | 0.0 |
| concepts[23].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[23].display_name | Epistemology |
| concepts[24].id | https://openalex.org/C50522688 |
| concepts[24].level | 1 |
| concepts[24].score | 0.0 |
| concepts[24].wikidata | https://www.wikidata.org/wiki/Q189833 |
| concepts[24].display_name | Economic growth |
| concepts[25].id | https://openalex.org/C192562407 |
| concepts[25].level | 0 |
| concepts[25].score | 0.0 |
| concepts[25].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[25].display_name | Materials science |
| concepts[26].id | https://openalex.org/C2524010 |
| concepts[26].level | 1 |
| concepts[26].score | 0.0 |
| concepts[26].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[26].display_name | Geometry |
| concepts[27].id | https://openalex.org/C50644808 |
| concepts[27].level | 2 |
| concepts[27].score | 0.0 |
| concepts[27].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[27].display_name | Artificial neural network |
| concepts[28].id | https://openalex.org/C138885662 |
| concepts[28].level | 0 |
| concepts[28].score | 0.0 |
| concepts[28].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[28].display_name | Philosophy |
| concepts[29].id | https://openalex.org/C111919701 |
| concepts[29].level | 1 |
| concepts[29].score | 0.0 |
| concepts[29].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[29].display_name | Operating system |
| concepts[30].id | https://openalex.org/C127413603 |
| concepts[30].level | 0 |
| concepts[30].score | 0.0 |
| concepts[30].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[30].display_name | Engineering |
| concepts[31].id | https://openalex.org/C146978453 |
| concepts[31].level | 1 |
| concepts[31].score | 0.0 |
| concepts[31].wikidata | https://www.wikidata.org/wiki/Q3798668 |
| concepts[31].display_name | Aerospace engineering |
| concepts[32].id | https://openalex.org/C199360897 |
| concepts[32].level | 1 |
| concepts[32].score | 0.0 |
| concepts[32].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[32].display_name | Programming language |
| concepts[33].id | https://openalex.org/C48103436 |
| concepts[33].level | 2 |
| concepts[33].score | 0.0 |
| concepts[33].wikidata | https://www.wikidata.org/wiki/Q599031 |
| concepts[33].display_name | State (computer science) |
| keywords[0].id | https://openalex.org/keywords/extrapolation |
| keywords[0].score | 0.8228588104248047 |
| keywords[0].display_name | Extrapolation |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7131764888763428 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/gradient-descent |
| keywords[2].score | 0.5854052901268005 |
| keywords[2].display_name | Gradient descent |
| keywords[3].id | https://openalex.org/keywords/stateless-protocol |
| keywords[3].score | 0.5783516764640808 |
| keywords[3].display_name | Stateless protocol |
| keywords[4].id | https://openalex.org/keywords/range |
| keywords[4].score | 0.5169107913970947 |
| keywords[4].display_name | Range (aeronautics) |
| keywords[5].id | https://openalex.org/keywords/similarity |
| keywords[5].score | 0.5155006051063538 |
| keywords[5].display_name | Similarity (geometry) |
| keywords[6].id | https://openalex.org/keywords/regular-polygon |
| keywords[6].score | 0.5104607343673706 |
| keywords[6].display_name | Regular polygon |
| keywords[7].id | https://openalex.org/keywords/process |
| keywords[7].score | 0.4813709855079651 |
| keywords[7].display_name | Process (computing) |
| keywords[8].id | https://openalex.org/keywords/simple |
| keywords[8].score | 0.4795484244823456 |
| keywords[8].display_name | Simple (philosophy) |
| keywords[9].id | https://openalex.org/keywords/convergence |
| keywords[9].score | 0.4760172963142395 |
| keywords[9].display_name | Convergence (economics) |
| keywords[10].id | https://openalex.org/keywords/algorithm |
| keywords[10].score | 0.4675914943218231 |
| keywords[10].display_name | Algorithm |
| keywords[11].id | https://openalex.org/keywords/extension |
| keywords[11].score | 0.4655006527900696 |
| keywords[11].display_name | Extension (predicate logic) |
| keywords[12].id | https://openalex.org/keywords/descent |
| keywords[12].score | 0.44710758328437805 |
| keywords[12].display_name | Descent (aeronautics) |
| keywords[13].id | https://openalex.org/keywords/server |
| keywords[13].score | 0.43714290857315063 |
| keywords[13].display_name | Server |
| keywords[14].id | https://openalex.org/keywords/projection |
| keywords[14].score | 0.41466227173805237 |
| keywords[14].display_name | Projection (relational algebra) |
| keywords[15].id | https://openalex.org/keywords/data-mining |
| keywords[15].score | 0.3345091938972473 |
| keywords[15].display_name | Data mining |
| keywords[16].id | https://openalex.org/keywords/mathematics |
| keywords[16].score | 0.2219662070274353 |
| keywords[16].display_name | Mathematics |
| keywords[17].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[17].score | 0.19955188035964966 |
| keywords[17].display_name | Artificial intelligence |
| keywords[18].id | https://openalex.org/keywords/image |
| keywords[18].score | 0.16729208827018738 |
| keywords[18].display_name | Image (mathematics) |
| keywords[19].id | https://openalex.org/keywords/statistics |
| keywords[19].score | 0.13787740468978882 |
| keywords[19].display_name | Statistics |
| keywords[20].id | https://openalex.org/keywords/computer-network |
| keywords[20].score | 0.12465572357177734 |
| keywords[20].display_name | Computer network |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2301.09604 |
| 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 | https://arxiv.org/pdf/2301.09604 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2301.09604 |
| locations[1].id | doi:10.48550/arxiv.2301.09604 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2301.09604 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5079408504 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Divyansh Jhunjhunwala |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jhunjhunwala, Divyansh |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100443968 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2090-5512 |
| authorships[1].author.display_name | Shiqiang Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Shiqiang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5067441201 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6372-9697 |
| authorships[2].author.display_name | Gauri Joshi |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Joshi, Gauri |
| authorships[2].is_corresponding | False |
| 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/2301.09604 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | FedExP: Speeding Up Federated Averaging via Extrapolation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11612 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9994000196456909 |
| 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 | Stochastic Gradient Optimization Techniques |
| related_works | https://openalex.org/W3040374273, https://openalex.org/W2955572513, https://openalex.org/W1968270095, https://openalex.org/W4360604845, https://openalex.org/W4296478327, https://openalex.org/W151293476, https://openalex.org/W1960072520, https://openalex.org/W2042397106, https://openalex.org/W4361730764, https://openalex.org/W2015288657 |
| cited_by_count | 8 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 4 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 2 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2301.09604 |
| 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 | https://arxiv.org/pdf/2301.09604 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2301.09604 |
| primary_location.id | pmh:oai:arXiv.org:2301.09604 |
| 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 | https://arxiv.org/pdf/2301.09604 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2301.09604 |
| publication_date | 2023-01-23 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 39, 52, 60, 94, 147, 190 |
| abstract_inverted_index.FL | 104, 112, 194 |
| abstract_inverted_index.In | 88 |
| abstract_inverted_index.We | 114, 138 |
| abstract_inverted_index.an | 125 |
| abstract_inverted_index.as | 48, 146 |
| abstract_inverted_index.be | 144 |
| abstract_inverted_index.by | 44, 116 |
| abstract_inverted_index.in | 36, 84, 103, 171 |
| abstract_inverted_index.is | 155 |
| abstract_inverted_index.of | 59, 75, 169, 192 |
| abstract_inverted_index.on | 106, 189 |
| abstract_inverted_index.to | 14, 31, 38, 67, 96, 150, 157 |
| abstract_inverted_index.up | 159 |
| abstract_inverted_index.we | 91, 123 |
| abstract_inverted_index.Our | 161 |
| abstract_inverted_index.and | 20, 50, 130, 173, 186 |
| abstract_inverted_index.can | 143 |
| abstract_inverted_index.due | 13 |
| abstract_inverted_index.for | 8 |
| abstract_inverted_index.has | 29, 64, 80 |
| abstract_inverted_index.how | 141 |
| abstract_inverted_index.its | 15 |
| abstract_inverted_index.not | 81 |
| abstract_inverted_index.the | 4, 33, 57, 72, 76, 99, 111, 118, 131, 151, 167 |
| abstract_inverted_index.use | 58 |
| abstract_inverted_index.(FL) | 11 |
| abstract_inverted_index.Onto | 133 |
| abstract_inverted_index.Sets | 135 |
| abstract_inverted_index.also | 165 |
| abstract_inverted_index.been | 65, 82 |
| abstract_inverted_index.most | 5, 85 |
| abstract_inverted_index.seen | 83 |
| abstract_inverted_index.show | 140, 178 |
| abstract_inverted_index.size | 63, 79, 102 |
| abstract_inverted_index.step | 43, 54, 62, 78, 101 |
| abstract_inverted_index.than | 184 |
| abstract_inverted_index.that | 154, 179 |
| abstract_inverted_index.then | 139 |
| abstract_inverted_index.this | 89 |
| abstract_inverted_index.used | 156 |
| abstract_inverted_index.with | 24 |
| abstract_inverted_index.work | 28 |
| abstract_inverted_index.POCS. | 160 |
| abstract_inverted_index.While | 56 |
| abstract_inverted_index.based | 105 |
| abstract_inverted_index.begin | 115 |
| abstract_inverted_index.later | 164 |
| abstract_inverted_index.novel | 148 |
| abstract_inverted_index.range | 191 |
| abstract_inverted_index.shown | 66 |
| abstract_inverted_index.size. | 55 |
| abstract_inverted_index.speed | 158 |
| abstract_inverted_index.using | 51 |
| abstract_inverted_index.where | 122 |
| abstract_inverted_index.work, | 90 |
| abstract_inverted_index.(POCS) | 136 |
| abstract_inverted_index.Convex | 134 |
| abstract_inverted_index.FedAvg | 37, 129, 185 |
| abstract_inverted_index.FedExP | 142, 170, 180 |
| abstract_inverted_index.Recent | 27 |
| abstract_inverted_index.client | 46 |
| abstract_inverted_index.convex | 120 |
| abstract_inverted_index.faster | 183 |
| abstract_inverted_index.method | 95 |
| abstract_inverted_index.reveal | 124 |
| abstract_inverted_index.secure | 25 |
| abstract_inverted_index.server | 53, 61, 77, 100 |
| abstract_inverted_index.simple | 16 |
| abstract_inverted_index.sought | 30 |
| abstract_inverted_index.works. | 87 |
| abstract_inverted_index.FedExP, | 93 |
| abstract_inverted_index.benefit | 74 |
| abstract_inverted_index.between | 128 |
| abstract_inverted_index.descent | 42 |
| abstract_inverted_index.nature, | 19 |
| abstract_inverted_index.popular | 6 |
| abstract_inverted_index.present | 92 |
| abstract_inverted_index.privacy | 21 |
| abstract_inverted_index.provide | 68 |
| abstract_inverted_index.regime, | 121 |
| abstract_inverted_index.remains | 3 |
| abstract_inverted_index.results | 177 |
| abstract_inverted_index.updates | 47 |
| abstract_inverted_index.vanilla | 34 |
| abstract_inverted_index.varying | 108 |
| abstract_inverted_index.(FedAvg) | 2 |
| abstract_inverted_index.Learning | 10 |
| abstract_inverted_index.analysis | 163 |
| abstract_inverted_index.combined | 23 |
| abstract_inverted_index.existing | 86 |
| abstract_inverted_index.gradient | 41 |
| abstract_inverted_index.process. | 113 |
| abstract_inverted_index.treating | 45 |
| abstract_inverted_index.Averaging | 1 |
| abstract_inverted_index.Federated | 0, 9 |
| abstract_inverted_index.algorithm | 7 |
| abstract_inverted_index.averaging | 35 |
| abstract_inverted_index.baselines | 188 |
| abstract_inverted_index.competing | 187 |
| abstract_inverted_index.converges | 182 |
| abstract_inverted_index.datasets. | 195 |
| abstract_inverted_index.determine | 98 |
| abstract_inverted_index.discusses | 166 |
| abstract_inverted_index.extension | 149 |
| abstract_inverted_index.mechanism | 153 |
| abstract_inverted_index.motivated | 145 |
| abstract_inverted_index.practical | 73 |
| abstract_inverted_index.realistic | 193 |
| abstract_inverted_index.settings. | 175 |
| abstract_inverted_index.stateless | 18 |
| abstract_inverted_index.Projection | 132 |
| abstract_inverted_index.adaptively | 97 |
| abstract_inverted_index.algorithm. | 137 |
| abstract_inverted_index.generalize | 32 |
| abstract_inverted_index.guarantees | 22 |
| abstract_inverted_index.non-convex | 174 |
| abstract_inverted_index.similarity | 127 |
| abstract_inverted_index.throughout | 110 |
| abstract_inverted_index.considering | 117 |
| abstract_inverted_index.dynamically | 107 |
| abstract_inverted_index.generalized | 40 |
| abstract_inverted_index.improvement | 70 |
| abstract_inverted_index.interesting | 126 |
| abstract_inverted_index.performance | 69 |
| abstract_inverted_index.theoretical | 162 |
| abstract_inverted_index.Experimental | 176 |
| abstract_inverted_index.aggregation. | 26 |
| abstract_inverted_index.consistently | 181 |
| abstract_inverted_index.implications | 168 |
| abstract_inverted_index.optimization | 12 |
| abstract_inverted_index.extrapolation | 152 |
| abstract_inverted_index.theoretically, | 71 |
| abstract_inverted_index.implementation, | 17 |
| abstract_inverted_index.pseudo-gradients | 49, 109 |
| abstract_inverted_index.overparameterized | 119 |
| abstract_inverted_index.underparameterized | 172 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |