I'm a professor of Statistics at the Federal University of São Carlos (UFSCar), Brazil, and a CNPq Research Fellow. I did my PhD in Statistics at Carnegie Mellon University and now work at the intersection of machine learning and statistical inference.

My research focuses on making predictions more reliable and informative — especially when models face uncertainty, selection bias, or missing likelihoods. I’ve applied these ideas in areas ranging from astronomy to public health, and published in journals like JMLR, EJS, JCGS and AOAS, as well as ML conferences such as ICML, AISTATS and UAI.

I also enjoy teaching and mentoring students, and I wrote a machine learning textbook in Portuguese used in several universities across Brazil. I also have a book in English about Uncertainty Quantification in ML.

More about me (and free course materials) at rafaelizbicki.com.