Quantifying identifiability in independent component analysis

DOI10.1214/14-EJS932zbMath1298.62045arXiv1401.7899WikidataQ57707406 ScholiaQ57707406MaRDI QIDQ405369

Benjamin Falkeborg, Alexander Sokol, Marloes H. Maathuis

Publication date: 5 September 2014

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1401.7899

zbMATH Keywords

independent component analysisempirical processidentifiabilityasymptotic statisticscontaminated distributionKolmogorov normlinear structural equation modellingam

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Robustness and adaptive procedures (parametric inference) (62F35)

Related Items

Maximum independent component analysis with application to EEG data

Uses Software

• FastICA
• DirectLiNGAM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Semiparametrically efficient inference based on signed ranks in symmetric independent component models
• Independent component analysis via nonparametric maximum likelihood estimation
• A note on strong approximations of multivariate empirical processes
• Independent component analysis, a new concept?
• Weak convergence and empirical processes. With applications to statistics
• Efficient independent component analysis
• Weak convergence of probabilities on nonseparable metric spaces and empirical measures on Euclidean spaces
• Independent component analysis: recent advances
• On the identifiability of additive index models
• Multiparameter Processes
• Compact CramÉr–Rao Bound Expression for Independent Component Analysis
• Identifiability of Gaussian structural equation models with equal error variances