AMLab | Amsterdam Machine Learning Lab

Metod Jazbec

PhD candidate (advised by Eric Nalisnick, Dan Zhang, and Stephan Mandt)
AMLab, Delta Lab
Informatics Institute
University of Amsterdam
Science Park, Lab 42, L4.59

Personal page Google scholar Github Twitter

I am a PhD student in Machine Learning at Amsterdam Machine Learning Lab (AMLab) and Delta Lab, supervised by Eric Nalisnick, Dan Zhang, and Stephan Mandt. I am interested in bayesian deep learning, more specifically in developing systems that can provide best uncertainty estimations under given computational constraints.

Selected Publications

AISTATS

Scalable gaussian process variational autoencoders

Jazbec, Metod, Ashman, Matt, Fortuin, Vincent, Pearce, Michael, Mandt, Stephan, and Rätsch, Gunnar

In International Conference on Artificial Intelligence and Statistics (AISTATS) Mar 2021

Abs HTML PDF Code

Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GPVAEs has led to significant improvements in this regard, but is still inhibited by the intrinsic complexity of exact GP inference. We improve the scalability of these methods through principled sparse inference approaches. We propose a new scalable GPVAE model that outperforms existing approaches in terms of runtime and memory footprint, is easy to implement, and allows for joint end-to-end optimization of all components.