Learning Bijective Feature Maps for Linear ICA
arXiv:2002.07766
Abstract
Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing probabilistic deep generative models (DGMs), which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. Given the complexities of jointly training such a hybrid model, we introduce novel theory that constrains linear ICA to lie close to the manifold of orthogonal rectangular matrices, the Stiefel manifold. By doing so we create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.
arXiv comment8 pages
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- NICE: Non-linear Independent Components Estimation
- Variational Inference with Normalizing Flows
- Disentangling by Factorising
- Normalizing Flows for Probabilistic Modeling and Inference
- Structured Disentangled Representations
- Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
- Generalized BackPropagation, Étude De Cas: Orthogonality
- Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform
- Accelerated Optimization With Orthogonality Constraints
- Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations