RICA replaces ICA's global generative model with local Riemannian geometry, introducing a disentanglement tensor based on the Hessian of the log-likelihood and Ricci curvature to measure pointwise disentanglement, which recovers sources across manifolds in controlled tests.
Nonlinear independent component analysis: Existence and uniqueness results.Neural Netw., 12(3):429–439, apr 1999
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Two auxiliary environments suffice to identify causal graphs and functional mechanisms in structural causal models under acyclicity and invariance assumptions, enabling correct counterfactual inference.
citing papers explorer
-
Disentanglement Beyond Generative Models with Riemannian ICA
RICA replaces ICA's global generative model with local Riemannian geometry, introducing a disentanglement tensor based on the Hessian of the log-likelihood and Ricci curvature to measure pointwise disentanglement, which recovers sources across manifolds in controlled tests.
-
Causal Learning with the Invariance Principle
Two auxiliary environments suffice to identify causal graphs and functional mechanisms in structural causal models under acyclicity and invariance assumptions, enabling correct counterfactual inference.