Partial Optimality in Cubic Correlation Clustering.

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Abstract

The higher-order correlation clustering problem is an expressive model, and recently, local search heuristics have been proposed for several applications. Certifying optimality, however, is NP-hard and practically hampered already by the complexity of the problem statement. Here, we focus on establishing partial optimality conditions for the special case of complete graphs and cubic objective functions. In addition, we define and implement algorithms for testing these conditions and examine their effect numerically, on two datasets.

Details

OriginalspracheEnglisch
TitelProceedings of the 40th International Conference on Machine Learning
Seiten32598-32617
Seitenumfang20
PublikationsstatusVeröffentlicht - 2023
Peer-Review-StatusJa

Publikationsreihe

ReiheProceedings of Machine Learning Research
Band202

Externe IDs

ORCID /0000-0001-5036-9162/work/143781902
Scopus 85174390005