Identifiability of latent-variable and structural-equation models: from linear to nonlinear

no code implementations • 6 Feb 2023 • Aapo Hyvärinen, Ilyes Khemakhem, Ricardo Monti

An old problem in multivariate statistics is that linear Gaussian models are often unidentifiable, i. e. some parameters cannot be uniquely estimated.

Time Series Time Series Analysis

Robust contrastive learning and nonlinear ICA in the presence of outliers

no code implementations • 1 Nov 2019 • Hiroaki Sasaki, Takashi Takenouchi, Ricardo Monti, Aapo Hyvärinen

We develop two robust nonlinear ICA methods based on the {\gamma}-divergence, which is a robust alternative to the KL-divergence in logistic regression.

Causal Discovery Contrastive Learning +2