Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
auxiliary signalscausal representation learningconvex geometrydiverse influence component analysisidentifiabilityinfluence diversityjacobianjacobian sparsityjacobian volume maximizationlatent component identificationlatent component independencemixing functionnonlinear independent component analysisnonlinear mixturesself-supervised learningstructural assumptions
Latent component identification from unknown *nonlinear* mixtures is a foundational challenge in machine learning, with applications in tasks such as self-supervised learning and causal representation learning. Prior work in *nonlinear independent component analysis* (nICA) has shown that auxiliary signals