Coulomb Autoencoders
arXiv:1802.03505
Abstract
Learning the true density in high-dimensional feature spaces is a well-known problem in machine learning. In this work, we consider generative autoencoders based on maximum-mean discrepancy (MMD) and provide theoretical insights. In particular, (i) we prove that MMD coupled with Coulomb kernels has optimal convergence properties, which are similar to convex functionals, thus improving the training of autoencoders, and (ii) we provide a probabilistic bound on the generalization performance, highlighting some fundamental conditions to achieve better generalization. We validate the theory on synthetic examples and on the popular dataset of celebrities' faces, showing that our model, called Coulomb autoencoders, outperform the state-of-the-art.
References in corpus (12)
- Auto-Encoding Variational Bayes
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- MMD GAN: Towards Deeper Understanding of Moment Matching Network
- Unrolled Generative Adversarial Networks
- Generative Moment Matching Networks
- Training generative neural networks via Maximum Mean Discrepancy optimization
- The Numerics of GANs
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
- Geometric GAN
- Generative Multi-Adversarial Networks