New EMS Coreset algorithm offers efficient data subsetting for machine learning

Researchers have developed EMS Coreset, a novel algorithm designed to create representative data subsets for machine learning tasks more efficiently. This method utilizes an expectation-maximization approach with Sinkhorn regularization, allowing for non-uniform coreset weights and providing a generalized k-means clustering solution. The algorithm demonstrates competitive approximation quality and robustness while significantly reducing computation time compared to existing Wasserstein and standard Sinkhorn coreset selection techniques, particularly for large datasets. AI

IMPACT This new coreset selection method could enable more efficient training of machine learning models on large datasets.

RANK_REASON The cluster contains a research paper detailing a new algorithm for machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv stat.ML →

• arXiv
• EMS Coreset
• expectation–maximization algorithm
• k-means clustering
• optimal transport
• Sinkhorn
• Wasserstein

• paper
• infra

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