EDITORIAL Editorial I was not able to attend GECCO this year, but everybody told me it was as great as usual and I am sure that all the people who attended it enjoyed it a lot! I had not spent the second week of July in Milan since 2000, when I could not attend GECCO-2000 in Las Vegas. Thus, spending the GECCO week at work while all my friends were enjoying themselves in Philly, has been kind o...

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...