
Probabilistic Spatial Transformers for Bayesian Data Augmentation
Highcapacity models require vast amounts of data, and data augmentation...
read it

Geodesic Clustering in Deep Generative Models
Deep generative models are tremendously successful in learning lowdimen...
read it

Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)
We investigate learning of the differential geometric structure of a dat...
read it

Latent Space Oddity: on the Curvature of Deep Generative Models
Deep generative models provide a systematic way to learn nonlinear data ...
read it

Intrinsic Grassmann Averages for Online Linear and Robust Subspace Learning
Principal Component Analysis (PCA) is a fundamental method for estimatin...
read it

A Locally Adaptive Normal Distribution
The multivariate normal density is a monotonic function of the distance ...
read it

Metrics for Probabilistic Geometries
We investigate the geometrical structure of probabilistic generative dim...
read it

Dreaming More Data: Classdependent Distributions over Diffeomorphisms for Learned Data Augmentation
Data augmentation is a key element in training highdimensional models. ...
read it

Probabilistic Solutions to Differential Equations and their Application to Riemannian Statistics
We study a probabilistic numerical method for the solution of both bound...
read it

Geodesic Exponential Kernels: When Curvature and Linearity Conflict
We consider kernel methods on general geodesic metric spaces and provide...
read it

Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable models
Latent variable models learn a stochastic embedding from a lowdimension...
read it

Fast and Robust Shortest Paths on Manifolds Learned from Data
We propose a fast, simple and robust algorithm for computing shortest pa...
read it

Expected path length on random manifolds
Manifold learning seeks a low dimensional representation that faithfully...
read it

Variational Autoencoders with Riemannian Brownian Motion Priors
Variational Autoencoders (VAEs) represent the given data in a lowdimens...
read it

Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
We propose a fully generative model where the latent variable respects b...
read it
Søren Hauberg
is this you? claim profile