56 citations · 199 across the 40 of their papers we have counts for
11 papers · 1 filter
Learning Distances from Data with Normalizing Flows and Score Matching
Peter Sorrenson, Daniel Behrend-Uriarte, Christoph Schnörr +1
Density-based distances (DBDs) provide a principled approach to metric learning by defining distances in terms of the underlying data distribution. By employing a Riemannian metric…
Generative Modeling of Discrete Joint Distributions by E-Geodesic Flow Matching on Assignment Manifolds
Bastian Boll, Daniel Gonzalez-Alvarado, Christoph Schnörr
This paper introduces a novel generative model for discrete distributions based on continuous normalizing flows on the submanifold of factorizing discrete measures. Integration of…
On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows
Felix Draxler, Stefan Wahl, Christoph Schnörr +1
We present a novel theoretical framework for understanding the expressive power of normalizing flows. Despite their prevalence in scientific applications, a comprehensive understan…
On the Convergence Rate of Gaussianization with Random Rotations
Felix Draxler, Lars Kühmichel, Armand Rousselot +3
Gaussianization is a simple generative model that can be trained without backpropagation. It has shown compelling performance on low dimensional data. As the dimension increases, h…
Whitening Convergence Rate of Coupling-based Normalizing Flows
Felix Draxler, Christoph Schnörr, Ullrich Köthe
Coupling-based normalizing flows (e.g. RealNVP) are a popular family of normalizing flow architectures that work surprisingly well in practice. This calls for theoretical understan…
Learning System Parameters from Turing Patterns
David Schnörr, Christoph Schnörr
The Turing mechanism describes the emergence of spatial patterns due to spontaneous symmetry breaking in reaction-diffusion processes and underlies many developmental processes. Id…
Learning Linearized Assignment Flows for Image Labeling
Alexander Zeilmann, Stefania Petra, Christoph Schnörr
We introduce a novel algorithm for estimating optimal parameters of linearized assignment flows for image labeling. An exact formula is derived for the parameter gradient of any lo…
Self-Assignment Flows for Unsupervised Data Labeling on Graphs
Matthias Zisler, Artjom Zern, Stefania Petra +1
This paper extends the recently introduced assignment flow approach for supervised image labeling to unsupervised scenarios where no labels are given. The resulting self-assignment…
Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment
Artjom Zern, Matthias Zisler, Stefania Petra +1
This paper introduces the unsupervised assignment flow that couples the assignment flow for supervised image labeling with Riemannian gradient flows for label evolution on feature…
Image Labeling Based on Graphical Models Using Wasserstein Messages and Geometric Assignment
Ruben Hühnerbein, Fabrizio Savarino, Freddie Åström +1
We introduce a novel approach to Maximum A Posteriori inference based on discrete graphical models. By utilizing local Wasserstein distances for coupling assignment measures across…
Learning Arbitrary Sum-Product Network Leaves with Expectation-Maximization
Mattia Desana, Christoph Schnörr
Sum-Product Networks with complex probability distribution at the leaves have been shown to be powerful tractable-inference probabilistic models. However, while learning the intern…