Skip to yearly menu bar Skip to main content


Flat Metric Minimization with Applications in Generative Modeling

Thomas Möllenhoff · Daniel Cremers

Pacific Ballroom #16

Keywords: [ Unsupervised Learning ] [ Representation Learning ] [ Optimization - Others ] [ Generative Adversarial Networks ] [ Deep Generative Models ]


We take the novel perspective to view data not as a probability distribution but rather as a current. Primarily studied in the field of geometric measure theory, k-currents are continuous linear functionals acting on compactly supported smooth differential forms and can be understood as a generalized notion of oriented k-dimensional manifold. By moving from distributions (which are 0-currents) to k-currents, we can explicitly orient the data by attaching a k-dimensional tangent plane to each sample point. Based on the flat metric which is a fundamental distance between currents, we derive FlatGAN, a formulation in the spirit of generative adversarial networks but generalized to k-currents. In our theoretical contribution we prove that the flat metric between a parametrized current and a reference current is Lipschitz continuous in the parameters. In experiments, we show that the proposed shift to k>0 leads to interpretable and disentangled latent representations which behave equivariantly to the specified oriented tangent planes.

Live content is unavailable. Log in and register to view live content