Metod Jazbec

I am a PhD student at Amsterdam Machine Learning Lab where I am fortunate to be supervised by Eric Nalisnick, and co-supervised by Dan Zhang (Bosch AI) and Stephan Mandt (UC Irvine).

Previously, I completed my Masters in Data Science at ETH Zurich and gained industry experience working as a data scientist and quantitative engineer.

My main current research goal is to build ML systems that can reason about uncertainty in real time. Other interests include, but are not limited to, probabilistic ML, (scalable) Bayesian inference, and generative modelling.

selected publications

NeurIPS

Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity

Metod Jazbec, James Urquhart Allingham, Dan Zhang, and Eric Nalisnick

Advances in Neural Information Processing Systems (NeurIPS) 2023

Abs HTML Code

Modern predictive models are often deployed to environments in which computational budgets are dynamic. Anytime algorithms are well-suited to such environments as, at any point during computation, they can output a prediction whose quality is a function of computation time. Early-exit neural networks have garnered attention in the context of anytime computation due to their capability to provide intermediate predictions at various stages throughout the network. However, we demonstrate that current early-exit networks are not directly applicable to anytime settings, as the quality of predictions for individual data points is not guaranteed to improve with longer computation. To address this shortcoming, we propose an elegant post-hoc modification, based on the Product-of-Experts, that encourages an early-exit network to become gradually confident. This gives our deep models the property of conditional monotonicity in the prediction quality – an essential stepping stone towards truly anytime predictive modeling using early-exit architectures. Our empirical results on standard image-classification tasks demonstrate that such behaviors can be achieved while preserving competitive accuracy on average.
AISTATS

Scalable gaussian process variational autoencoders

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

International Conference on Artificial Intelligence and Statistics (AISTATS) 2021

Abs HTML 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.