NeurIPS paper accepted

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.

MLSP paper accepted

Paper accepted for MLSP, together with Jakob Lindqvist, Amanda Olmin and Lennart Svensson! We develop a general framework for ensemble distillation that, instead of distilling the ensemble into a single predictive model, retain the distribution over the ensemble members. This provides a more complete description of the predictive uncertainty, making the model more robust and enables epistemic uncertainty quantification. Preprint is available here.

WASP Industrial PhD Project with Veoneer AB

I’m very happy to accounce my application together with Veoneer AB for a WASP Industrial PhD project got accepted! In August, Hariprasath Govindarajan will join Veoneer and STIMA as an industrial PhD student, working on the project Attentive and Disentangled Representation Learning. Welcome Hari! The company supervisor is Jacob Roll.