A
Antti J. Kerminen
Researcher at Helsinki Institute for Information Technology
Publications - 5
Citations - 1448
Antti J. Kerminen is an academic researcher from Helsinki Institute for Information Technology. The author has contributed to research in topics: Causal model & Latent variable. The author has an hindex of 5, co-authored 5 publications receiving 1129 citations.
Papers
More filters
Journal ArticleDOI
A Linear Non-Gaussian Acyclic Model for Causal Discovery
TL;DR: This work shows how to discover the complete causal structure of continuous-valued data, under the assumptions that (a) the data generating process is linear, (b) there are no unobserved confounders, and (c) disturbance variables have non-Gaussian distributions of non-zero variances.
Journal ArticleDOI
Estimation of causal effects using linear non-Gaussian causal models with hidden variables
TL;DR: It is shown that, with non-Gaussian data, causal inference is possible even in the presence of hidden variables (unobserved confounders), even when the existence of such variables is unknown a priori.
Proceedings Article
Estimation of linear, non-gaussian causal models in the presence of confounding latent variables.
TL;DR: The estimation of linear causal models from data is discussed, and an algorithm for estimating this set of models is developed, and numerical simulations which confirm the theoretical arguments and demonstrate the practical viability of the approach are described.
Book ChapterDOI
Testing significance of mixing and demixing coefficients in ICA
TL;DR: Testing significance of mixing and demixing coefficients in ICA is discussed and a proposed test statistics to examine significance of these coefficients statistically statistically is proposed.
Posted Content
Estimation of linear, non-gaussian causal models in the presence of confounding latent variables
TL;DR: In this article, the authors discuss the estimation of the model when confounding latent variables are present and develop an algorithm for estimating this set, and describe numerical simulations which confirm the theoretical arguments and demonstrate the practical viability of the approach.