I hold the position of Laplace Postdoctoral Chair in Data Science at École normale supérieure in Paris, where I work with Emmanuel Dupoux and the CoML team. Before that, I was a PhD student at Carnegie Mellon University in Graham Neubig's NeuLab. In the past, I have also interned at Facebook and Deepmind. You can find my full CV here and the list of my publications there or on Google scholar.
My main area of interest revolves around developing machine learning models that can handle non-stationary data distributions, with a particular focus on natural language processing applications. Following this leitmotiv I have worked on distributional shift in the form of domain shift, adversarial perturbations and more recently continual learning of multiple tasks. I have also developed a recent interest in emergent communication.
I also used to be an active contributor of DyNet, a toolkit for dynamic neural networks. Check it out!
Other than that I like reading sci-fi, sleeping, eating and playing video games. Recently I've picked up miniature painting and watercolor painting.
Before studying at CMU, I was an "Élève ingènieur" at École polytechnique in France.
My email is
pmichel31415[at]gmail.com. You can also find me on Twitter, where I mostly tweet about my own work.
- I successfully defended my PhD thesis! Many thanks to my thesis committee members, Graham Neubig, Tatsunori Hashimoto, Zachary Lipton and Zico Kolter. Full thesis document now on arxiv.
- I released the camera ready version of our paper Modeling the Second Player in Distributionally Robust Optimization. Code available on github.
- I gave a talk at the NLP with Friends online seminar on our ongoing work on parametric distributionally robust optimization. The talk was recorded and can be found on Youtube.
Some projects I've been doing on the side (not so) recently: