Jovana Mitrovic

Jovana Mitrovic

Kernel methods, deep learning

I am a third year DPhil student supervised by Dino Sejdinovic and Yee Whye Teh. My research interests encompass kernel methods and deep learning. In particular, I have worked/am working on kernel-based summary statistics construction, inference methods for generative adversarial networks and weight initialization methods for neural networks.



  • J. Mitrovic, D. Sejdinovic, Y. W. Teh, Deep Kernel Machines via the Kernel Reparametrization Trick, in International Conference on Learning Representations (ICLR) Workshop Track, 2017.


  • J. Mitrovic, D. Sejdinovic, Y. W. Teh, DR-ABC: Approximate Bayesian Computation with Kernel-Based Distribution Regression, in International Conference on Machine Learning (ICML), 2016, 1482–1491.
    Project: bigbayes