Under logarithmic loss, PCA on heavy-tailed observations from the superstatistical model recovers the principal directions of the underlying Gaussian generator's covariance.
Analysis of a complex of statistical variables into principal components,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Extends IPC to stationary physical systems with capacity bounds, asymptotic bias analysis, Richardson/Sobol estimators, and photonic validation linking total IPC to ML performance and effective dimensionality.
citing papers explorer
-
Heavy-Tailed Principal Component Analysis
Under logarithmic loss, PCA on heavy-tailed observations from the superstatistical model recovers the principal directions of the underlying Gaussian generator's covariance.
-
Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration
Extends IPC to stationary physical systems with capacity bounds, asymptotic bias analysis, Richardson/Sobol estimators, and photonic validation linking total IPC to ML performance and effective dimensionality.