Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the
data distribution during learning. This phenomenon has long been considered a major …

Variational inference (VI) has become the method of choice for fitting many modern
probabilistic models. However, practitioners are faced with a fragmented literature that offers …

The proliferation of computing devices has brought about an opportunity to deploy machine
learning models on new problem domains using previously inaccessible data. Traditional …

Bayesian models are established as one of the main successful paradigms for complex
problems in machine learning. To handle intractable inference, research in this area has …

The stochastic variational inference (SVI) paradigm, which combines variational inference,
natural gradients, and stochastic updates, was recently proposed for large-scale data …

Graphical models are powerful tools to describe high-dimensional data; they provide a
compact graphical representation of the interactions between different variables and such …

Work over the last two decades has resulted in the development of powerful models in
probabilistic machine learning with a variety of applications: recommender systems …