A Non-Convex Optimization Approach to Correlation Clustering
Paper i proceeding, 2019

We develop a non-convex optimization approach to correlation clustering using the Frank-Wolfe (FW) framework. We show that the basic approach leads to a simple and natural local search algorithm with guaranteed convergence. This algorithm already beats alternative algorithms by substantial margins in both running time and quality of the clustering. Using ideas from FW algorithms, we develop subsampling and variance reduction paradigms for this approach. This yields both a practical improvement of the algorithm and some interesting further directions to investigate. We demonstrate the performance on both synthetic and real world data sets.

Författare

Erik Thiel

Chalmers, Data- och informationsteknik, Data Science

Morteza Haghir Chehreghani

Chalmers, Data- och informationsteknik, Data Science

Devdatt Dubhashi

Chalmers, Data- och informationsteknik, Data Science

THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

5159-5166

33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence
Honolulu, USA,

Ämneskategorier

Data- och informationsvetenskap

Mer information

Senast uppdaterat

2019-12-06