Statistics of Min-max Normalized Eigenvalues in Random Matrices
By: Hyakka Nakada, Shu Tanaka
Random matrix theory has played an important role in various areas of pure mathematics, mathematical physics, and machine learning. From a practical perspective of data science, input data are usually normalized prior to processing. Thus, this study investigates the statistical properties of min-max normalized eigenvalues in random matrices. Previously, the effective distribution for such normalized eigenvalues has been proposed. In this study, we apply it to evaluate a scaling law of the cumulative distribution. Furthermore, we derive the residual error that arises during matrix factorization of random matrices. We conducted numerical experiments to verify these theoretical predictions.
Similar Papers
CLT for LES of real valued random centrosymmetric matrices
Probability
Finds math patterns in complex data.
On eigenvalues of a renormalized sample correlation matrix
Statistics Theory
Finds if data is related, even with lots of info.
Evaluating Singular Value Thresholds for DNN Weight Matrices based on Random Matrix Theory
Machine Learning (Stat)
Cleans up computer brains for better learning.