Metod Jazbec

I am a PhD student at Amsterdam Machine Learning Lab. I am fortunate to be supervised by Eric Nalisnick, and co-supervised by Dan Zhang and Stephan Mandt.

Previously, I completed my Masters in Data Science at ETH Zurich and gained industry experience working as a data scientist and quantitative engineer. I was also a research intern at Microsoft (Cambridge, UK).

Main topics of interest include: efficient AI, uncertainty quantification, generative modeling .

selected publications

NeurIPS

Fast yet Safe: Early-Exiting with Risk Control

Metod Jazbec*, Alexander Timans*, Tin Hadži Veljković, Kaspar Sakmann, Dan Zhang, Christian A. Naesseth, and Eric Nalisnick

2024

Abs HTML Code

Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural networks (EENNs) offer a promising solution: they accelerate inference by allowing intermediate layers to exit and produce a prediction early. Yet a fundamental issue with EENNs is how to determine when to exit without severely degrading performance. In other words, when is it ’safe’ for an EENN to go ’fast’? To address this issue, we investigate how to adapt frameworks of risk control to EENNs. Risk control offers a distribution-free, post-hoc solution that tunes the EENN’s exiting mechanism so that exits only occur when the output is of sufficient quality. We empirically validate our insights on a range of vision and language tasks, demonstrating that risk control can produce substantial computational savings, all the while preserving user-specified performance goals.
NeurIPS

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

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

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.