New Gromov-Wasserstein quantization method extends k-means clustering

A new paper introduces Gromov-Wasserstein (GW) quantization as an extension of traditional k-means clustering. This method not only clusters data points but also considers the ambient geometry of the space, offering new modeling possibilities. The research provides theoretical guarantees for GW quantization and an algorithm analogous to Lloyd's algorithm for numerical approximation, demonstrating its utility in applications like analyzing 3D shapes and pruning neural networks. AI

IMPACT Introduces a novel clustering technique with potential applications in structured pruning of neural networks.

RANK_REASON The cluster contains a single academic paper detailing a new mathematical method for clustering. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• DagsHub
• Gromov--Wasserstein
• Hugging Face
• k-means clustering
• Lloyd's algorithm
• Stephan Eckstein
• Wasserstein metric

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →