Identifiability

Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA

This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the …

Sébastien Lachapelle, Pau Rodriguez, Yash Sharma, Katie Everett , Rémi Le Priol, Alexandre Lacoste, Simon Lacoste-Julien

Causal Learning and Reasoning (CLeaR), 2022.