On Oct 28 my PhD student David Widmann successfully defended his licentiate’s thesis (= roughly half way to PhD), entitled Calibration of Probabilistic Predictive Models. The discussion was lead by Meelis Kull, University of Tartu.
Congratulations to Johanna Rosén who has been granted 29 MSEK from the KAW foundation for The 2D-Materials Frontier. Together with co-applicant Fredrik Heintz I’m responsible for the machine learning part of the project, where we will use machine learning to aid the search for new and exciting 2D materials.
Paper accepted for NeurIPS, together with Christian A Naesseth and David M Blei! We develop a method for optimizing the “inclusive” Kullback-Leibler divergence KL(p || q) in the context of variational inference by blending VI and MCMC. Check out the paper here.