New statistical methods estimate multiple high-dimensional means

Researchers have developed new statistical methods for estimating multiple multi-dimensional means from independent samples. Their approach utilizes convex combinations of empirical means, with weights determined by either a testing procedure to identify low-variance neighboring means or by minimizing an upper confidence bound on the quadratic risk. Theoretical analysis indicates that these methods offer an asymptotic improvement in quadratic risk compared to simple empirical means, particularly as the data's effective dimension increases. The efficacy of these techniques was demonstrated through experiments involving simulated data and real-world datasets, including the estimation of multiple kernel mean embeddings. AI

RANK_REASON The item is an academic paper submitted to arXiv detailing statistical methods. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv stat.ML →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• Jean-Baptiste Fermanian
• ScienceCast

• paper
• other

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