A generative model’s partition function is typically expressed as an intractable multi-dimensional integral, whose approximation presents a challenge to numerical and Monte Carlo integration. In this work, we propose a new estimation method for intractable partition functions, based on distilling an intractable generative model into a tractable approximation thereof, and using the latter for pr...

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like to replace such cumbersome models with simpler models that perform equally well. In this thesis, we study knowledge distillation, the idea of extracting the...

Since Fermions are based on anti-commutation relations, their entanglement can not be studied in the usual way, such that the available theory has to be modified appropriately. Recent publications consider in particular the structure of separable and of maximally entangled states. In this talk we want to discuss local operations and entanglement distillation from bipartite, Fermionic systems. T...

We report on a method for utilising corpora collected in natural settings. It is based on distilling (re-writing) natural dialogues to elicit the type of dialogue that would occur if one the dialogue participants was a computer instead of a human. The method is a complement to other means such asWizard of Oz-studies and un-distilled natural dialogues. We present the distilling method and guidel...