About me


Hi, my name is Alexia and I’m a researcher in statistics and artificial intelligence. As of Winter 2019, I am starting a PhD at the Montreal Institute for Learning Algorithms (MILA). I have backgrounds in both statistics and computer science (BSc in Math and CS, MSc in Statistics). I have expertise in both Biostatistics (focused on Gene-by-environment interaction modelling) and Artificial Intelligence (focused on generative modelling).

I’m particularly interested in deep generative models. Deep generative models are all about findings ways to generate images, sound, video or text. It is so much more rewarding to generate something, than to try to predict something. It also has so much artistic potential. Imagine generating a potential new episode of TNG using only a written script and voice samples! We are extremely far from such capabilities but maybe one day…

Some of my previous work include Relativistic GANs, the LEGIT model trained using alternating optimization, and a study of the prior of Bayesian Trees. I also generated pictures of cats using several types of Generative Adversarial Networks (GAN).