264 citations · 937 across the 33 of their papers we have counts for
10 papers · 1 filter
A Review of Change of Variable Formulas for Generative Modeling
Ullrich Köthe
Change-of-variables (CoV) formulas allow to reduce complicated probability densities to simpler ones by a learned transformation with tractable Jacobian determinant. They are thus…
Lifting Architectural Constraints of Injective Flows
Peter Sorrenson, Felix Draxler, Armand Rousselot +3
Normalizing Flows explicitly maximize a full-dimensional likelihood on the training data. However, real data is typically only supported on a lower-dimensional manifold leading the…
Training Invertible Neural Networks as Autoencoders
The-Gia Leo Nguyen, Lynton Ardizzone, Ullrich Köthe
Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks. In this work,…
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…
Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data
Robert Schmier, Ullrich Köthe, Christoph-Nikolas Straehle
Detecting test data deviating from training data is a central problem for safe and robust machine learning. Likelihoods learned by a generative model, e.g., a normalizing flow via…
Benchmarking Invertible Architectures on Inverse Problems
Jakob Kruse, Lynton Ardizzone, Carsten Rother +1
Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems. Following up on this, we investigate how ten inverti…
Learning Robust Models Using The Principle of Independent Causal Mechanisms
Jens Müller, Robert Schmier, Lynton Ardizzone +2
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness i…
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
Peter Sorrenson, Carsten Rother, Ullrich Köthe
A central question of representation learning asks under which conditions it is possible to reconstruct the true latent variables of an arbitrarily complex generative process. Rece…
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
Lynton Ardizzone, Radek Mackowiak, Carsten Rother +1
The Information Bottleneck (IB) objective uses information theory to formulate a task-performance versus robustness trade-off. It has been successfully applied in the standard disc…
Analyzing Inverse Problems with Invertible Neural Networks
Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert +6
In many tasks, in particular in natural science, the goal is to determine hidden system parameters from a set of measurements. Often, the forward process from parameter- to measure…