Generative Adversarial Networks (GANs) is a novel class of deep generative models that
has recently gained significant attention. GANs learn complex and high-dimensional …

Disentangled representation learning has been proposed as an approach to learning
general representations even in the absence of, or with limited, supervision. A good general …

The key idea behind the unsupervised learning of disentangled representations is that real-
world data is generated by a few explanatory factors of variation which can be recovered by …

Image-to-image translation aims to learn the mapping between two visual domains. There
are two main challenges for many applications: 1) the lack of aligned training pairs and 2) …

We decompose the evidence lower bound to show the existence of a term measuring the
total correlation between latent variables. We use this to motivate the beta-TCVAE (Total …

We present new intuitions and theoretical assessments of the emergence of disentangled
representation in variational autoencoders. Taking a rate-distortion theory perspective, we …

How can intelligent agents solve a diverse set of tasks in a data-efficient manner? The
disentangled representation learning approach posits that such an agent would benefit from …

Intelligent agents should be able to learn useful representations by observing changes in
their environment. We model such observations as pairs of non-iid images sharing at least …

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be
able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to …

Learning an interpretable factorised representation of the independent data generative
factors of the world without supervision is an important precursor for the development of …