Deep Randomized Distributed Function Computation (DeepRDFC): Neural Distributed Channel Simulation

The randomized distributed function computation (RDFC) framework, which unifies many cutting-edge distributed computation and learning applications, is considered. An autoencoder (AE) architecture is proposed to minimize the total variation distance between the probability distribution simulated by...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / IEEE International Symposium on Information Theory S. 1 - 6
Hauptverfasser: Bergstrom, Didrik, Gunlu, Onur
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 22.06.2025
Schlagworte:
ISSN:2157-8117
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The randomized distributed function computation (RDFC) framework, which unifies many cutting-edge distributed computation and learning applications, is considered. An autoencoder (AE) architecture is proposed to minimize the total variation distance between the probability distribution simulated by the AE outputs and an unknown target distribution, using only data samples. We illustrate significantly high RDFC performance with communication load gains from our AEs compared to data compression methods. Our designs establish deep learning-based RDFC methods and aim to facilitate the use of RDFC methods, especially when the amount of common randomness is limited and strong function computation guarantees are required.
AbstractList The randomized distributed function computation (RDFC) framework, which unifies many cutting-edge distributed computation and learning applications, is considered. An autoencoder (AE) architecture is proposed to minimize the total variation distance between the probability distribution simulated by the AE outputs and an unknown target distribution, using only data samples. We illustrate significantly high RDFC performance with communication load gains from our AEs compared to data compression methods. Our designs establish deep learning-based RDFC methods and aim to facilitate the use of RDFC methods, especially when the amount of common randomness is limited and strong function computation guarantees are required.
Author Bergstrom, Didrik
Gunlu, Onur
Author_xml – sequence: 1
  givenname: Didrik
  surname: Bergstrom
  fullname: Bergstrom, Didrik
  email: didrik.bergstrom@liu.se
  organization: Information Theory and Security Laboratory (ITSL), Linköping University,Sweden
– sequence: 2
  givenname: Onur
  surname: Gunlu
  fullname: Gunlu, Onur
  email: onur.gunlu@liu.se
  organization: Information Theory and Security Laboratory (ITSL), Linköping University,Sweden
BookMark eNpVkD1PwzAYhA0Cibb0HyCREYYUf8SxzYYSApEqkNrslRO_FkaJE-VjgF9PKDBwy51Oem64JTrzrQeErgneEILVXb7Pi5hhKTcUUz53RPFY4hO0VkJJxgiPmFL4FC0o4SKUhIgLtByGd4yZYJguUJkCdMFOe9M27hNMkLph7F05jXPOJl-NrvVB0jbdNOpjvvkmdmmW3N4HLzD1uv7HJG_ae6iDvWum-khconOr6wHWv75CRfZYJM_h9vUpTx62oVNsDCm3swSPjeSMVlooUVlmKFjNuYkpUcZGlY04xZoLU0rNpRZSA0S0EgKzFbr6mXUAcOh61-j-4_B3CfsCyhhZQw
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ISIT63088.2025.11195680
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore: IEL
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore: IEL
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798331543990
EISSN 2157-8117
EndPage 6
ExternalDocumentID 11195680
Genre orig-research
GroupedDBID 6IE
6IH
6IK
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i93t-25ffff756d8532ca797cf3d2efa55d6219df4cf4520a57db8a58a78aee42c7703
IEDL.DBID RIE
IngestDate Wed Oct 29 06:13:08 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-25ffff756d8532ca797cf3d2efa55d6219df4cf4520a57db8a58a78aee42c7703
PageCount 6
ParticipantIDs ieee_primary_11195680
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle Proceedings / IEEE International Symposium on Information Theory
PublicationTitleAbbrev ISIT
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0037302
Score 1.9354861
Snippet The randomized distributed function computation (RDFC) framework, which unifies many cutting-edge distributed computation and learning applications, is...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Autoencoders
Computer architecture
Data compression
Design methodology
Heating systems
Image coding
Information theory
Network architecture
Probability distribution
Total variance
Title Deep Randomized Distributed Function Computation (DeepRDFC): Neural Distributed Channel Simulation
URI https://ieeexplore.ieee.org/document/11195680
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07a8MwEBZt6NApfaT0jYYO7eDEli3J7prUNFBCSELJFvQ4gSFxQpp06K-vpNgtGTrUkzAcBp3vPj3uuw-hBwrCohaNbKRBGCRM6CAzXAVESimYRRzpjy7e3_hgkE6n2bAiq3suDAD44jNou6G_y9dLtXVHZZ0o8uw2u0M_5JztyFp12o3tr0qqAq4ozDr9cX_CYhtDdg9IaLs23RNR8RiSN__59RPU-mXj4eEPzpyiAyjPULOWY8BVdJ4j2QNY4ZEo9XJRfIHGPdcU1-lZ2XFu8cv5AO_svD_wo7MY9fLu0zN2XTrEfM_GMQ9KmONxsahEvlpokr9Muq9BJaEQFFm8CQg19uGUaYvKRAmecWViTcAISjWz2UqbRJmEklBQrmUqaCp4KgASorhNBheoUS5LuESYSEMVTRLNuAU-GspY26VbqJQmJgagV6jlpmy22jXJmNWzdf3H-xt07Bzjqq4IuUWNzXoLd-hIfW6Kj_W9d-03-kSmKg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4MmugJf2D8bQ8e9DDYunXdvIILRCQEFsONdO1rsgQGQfDgX29bNg0HD-7ULHlZ8t7e-9bufe9D6IEC16hFPZ1p4DpByKUTKyYckmUZDzXiZPbo4r3PBoNoMomHJVndcmEAwDafQdMs7b98uRAbc1TW8jzLbtM79H0jnVXStarC6-uXlZQtXJ4bt3rjXhr6Oov0LpDQZmW8I6NiUSSp__P5x6jxy8fDwx-kOUF7UJyieiXIgMv8PENZB2CJR7yQi3n-BRJ3zFhco2il14lGMBMFvLWzEcGPxmLUSdpPz9jM6eCzHRvDPShghsf5vJT5aqA0eUnbXacUUXDy2F87hCp9MRpKjctEcBYzoXxJQHFKZajrlVSBUAElLqdMZhGnEWcRBwiIYLocnKNasSjgAmGSKSq032XINPRRN_Ol_nhzhZBE-QD0EjWMy6bL7ZiMaeWtqz_u36PDbvrWn_Z7g9drdGSCZHqwCLlBtfVqA7foQHyu84_VnQ3zN893qXM
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%2F+IEEE+International+Symposium+on+Information+Theory&rft.atitle=Deep+Randomized+Distributed+Function+Computation+%28DeepRDFC%29%3A+Neural+Distributed+Channel+Simulation&rft.au=Bergstrom%2C+Didrik&rft.au=Gunlu%2C+Onur&rft.date=2025-06-22&rft.pub=IEEE&rft.eissn=2157-8117&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FISIT63088.2025.11195680&rft.externalDocID=11195680