Learning Independent Features with Adversarial Nets for Non-linear ICA

Abstract

Reliable measures of statistical dependence could be useful tools for learning independent features and performing tasks like source separation using Independent Component Analysis (ICA). Unfortunately, many of such measures, like the mutual information, are hard to estimate and optimize directly. We propose to learn independent features with adversarial objectives which optimize such measures implicitly. These objectives compare samples from the joint distribution and the product of the marginals without the need to compute any probability densities. We also propose two methods for obtaining samples from the product of the marginals using either a simple resampling trick or a separate parametric distribution. Our experiments show that this strategy can easily be applied to different types of model architectures and solve both linear and non-linear ICA problems.

A preliminary version of this work was presented at the ICML 2017 workshop on implicit models

References in corpus (2)

• NICE: Non-linear Independent Components Estimation
• Invariant Representations for Noisy Speech Recognition

Cited by in corpus (7)

• Maximum Entropy Generators for Energy-Based Models
• Relevance Factor VAE: Learning and Identifying Disentangled Factors
• Learning Disentangled Representations via Mutual Information Estimation
• Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
• A Critical View of the Structural Causal Model
• Learning Diverse Representations for Fast Adaptation to Distribution Shift
• Analyzing the benefits of communication channels between deep learning models