AQOCI extends prior QOCI by adding Gauss-Seidel-style adaptive refinement to a QUBO formulation of centroid initialization, yielding up to 26% V-measure gains over k-means++ on MOTIF at small sample sizes and better results than k-means++ on heavily overlapping synthetic clusters.
Technical Report GT-CSE-08-01, Georgia Institute of Technology
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Quantum Optimized Centroid Initialization
AQOCI extends prior QOCI by adding Gauss-Seidel-style adaptive refinement to a QUBO formulation of centroid initialization, yielding up to 26% V-measure gains over k-means++ on MOTIF at small sample sizes and better results than k-means++ on heavily overlapping synthetic clusters.