Missing attributes are ubiquitous in causal inference, as they are in most applied statistical studies. In this work, we consider various sets of assumptions under which causal inference is possible despite missing attributes and discuss …
With increasing data availability, treatment causal effects can be evaluated across different datasets, both randomized trials and observational studies. Randomized trials isolate the effect of the treatment from that of unwanted (confounding) …
The simultaneous availability of experimental and observational data to estimate a treatment effect is both an opportunity and a statistical challenge: Combining the information gathered from both data is a promising avenue to build upon the internal …
We're excited to announce the Leveraging Observational Data with Machine Learning Virtual Workshop - brought to you by Michael Blum (Owkin), Julie Josse (Inria), and Raphael Porcher (Université de Paris) — on June 22nd and 23rd 2021! Register now (for free) & check out our great line-up of keynote speakers and panelists: Workshop website.
Dans le domaine de l’apprentissage machine, de grands progrès ont été réalisés dans l’obtention de modèles prédictifs puissants, mais ces modèles reposent sur des corrélations entre variables et ne permettent pas de comprendre les mécanismes …
I'm happy to officially share the great news that I'm a Google PhD fellow in Machine Learning this year. I'm very grateful for the support. Congrats to all the other awardees! And thanks of course to my great advisors and collaborators for their support: Julie Josse, Jean-Pierre Nadal, Jean-Philippe Vert, Stefan Wager, Tobias Gauss, and others.
In machine learning, there has been great progress in obtaining powerful predictive models, but these models rely on correlations between variables and do not allow for an understanding of the underlying mechanisms or how to intervene on the system …