How we choose to represent our data has a fundamental impact on our ability to
subsequently extract information from them. Machine learning promises to automatically …

Deep generative models provide a systematic way to learn nonlinear data distributions,
through a set of latent variables and a nonlinear" generator" function that maps latent points …

Neural samplers such as variational autoencoders (VAEs) or generative adversarial
networks (GANs) approximate distributions by transforming samples from a simple random …

We consider kernel methods on general geodesic metric spaces and provide both negative
and positive results. First we show that the common Gaussian kernel can only be …

A common assumption in generative models is that the generator immerses the latent space
into a Euclidean ambient space. Instead, we consider the ambient space to be a …

The inductive biases of trained neural networks are difficult to understand and,
consequently, to adapt to new settings. We study the inductive biases of linearizations of …

In complex transfer learning scenarios new tasks might not be tightly linked to previous
tasks. Approaches that transfer information contained only in the final parameters of a …

Bayesian neural networks often approximate the weight-posterior with a Gaussian
distribution. However, practical posteriors are often, even locally, highly non-Gaussian, and …

Variational Autoencoders (VAEs) represent the given data in a low-dimensional latent
space, which is generally assumed to be Euclidean. This assumption naturally leads to the …

Measuring the similarity between data points often requires domain knowledge, which can
in parts be compensated by relying on unsupervised methods such as latent-variable …