Siirry päänavigointiin Siirry hakuun Siirry pääsisältöön

Moreau Envelope ADMM for Decentralized Weakly Convex Optimization

  • Reza Mirzaeifard
  • , Naveen K.D. Venkategowda
  • , Alexander Jung*
  • , Stefan Werner
  • *Tämän työn vastaava kirjoittaja
  • Norwegian University of Science and Technology
  • Linköping University

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

This paper proposes a proximal variant of the alternating direction method of multipliers (ADMM) for distributed optimization. Although the current versions of ADMM algorithm provide promising numerical results in producing solutions that are close to optimal for many convex and non-convex optimization problems, it remains unclear if they can converge to a stationary point for weakly convex and locally non-smooth functions. Through our analysis using the Moreau envelope function, we demonstrate that MADM can indeed converge to a stationary point under mild conditions. Our analysis also includes computing the bounds on the amount of change in the dual variable update step by relating the gradient of the Moreau envelope function to the proximal function. Furthermore, the results of our numerical experiments indicate that our method is faster and more robust than widely-used approaches.

AlkuperäiskieliEnglanti
Otsikko2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
KustantajaIEEE
Sivut1126-1130
Sivumäärä5
ISBN (elektroninen)979-8-3503-0067-3
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaAsia-Pacific Signal and Information Processing Association Annual Summit and Conference - Taipei, Taiwan
Kesto: 31 lokak. 20233 marrask. 2023

Julkaisusarja

NimiProceedings / Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC
ISSN (elektroninen)2640-0103

Conference

ConferenceAsia-Pacific Signal and Information Processing Association Annual Summit and Conference
LyhennettäAPSIPA ASC
Maa/AlueTaiwan
KaupunkiTaipei
Ajanjakso31/10/202303/11/2023

Rahoitus

This work was supported by the Research Council of Norway.

Sormenjälki

Sukella tutkimusaiheisiin 'Moreau Envelope ADMM for Decentralized Weakly Convex Optimization'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä