Gianluigi Silvestri

Gianluigi Silvestri

PhD student in Machine Learning

OnePlanet Research Center


I am a PhD student in Machine Learning at OnePlanet Research Center and Donders Institute for Brain, Cognition and Behaviour. My research interests include Variational Inference, Normalizing Flows and Reinforcement Learning.

After a short carreer as professional Rugby player, and a couple of years as a DJ, I decided to study Computer Engineering, with the goal to specialize in audio and sound engineering. After watching the movie Ex Machina, I decided to study Machine Learning and AI instead, without really knowing what it was all about. I moved to Stockholm in 2017 for a Master’s degree in Machine Learning at KTH, and then worked as a Machine Learning engineer for the amazing startup Modulai. In December 2020 I moved to Nijmegen, in the Netherlands, to start a PhD in Probabilistic Machine Learning, becoming somehow a statistician (an unconscious one).

From Wikipedia: The law of the unconscious statistician, or LOTUS, is a theorem used to calculate the expected value of a function $g(X)$ of a random variable $X$ when one knows the probability distribution of $X$ but one does not know the distribution of $g(X)$: $$ E[g(X)]=\int_{-\infty}^{\infty}g(X)f_X(x)dx $$ This proposition is known as the law of the unconscious statistician because of a purported tendency to use the identity without realizing that it must be treated as the result of a rigorously proved theorem, not merely a definition.