publications

2024

  1. preprint
    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
  2. UAI
    Early-Exit Neural Networks with Nested Prediction Sets
    Metod Jazbec, Patrick Forré, Stephan Mandt, Dan Zhang, and Eric Nalisnick
    Uncertainty in Artificial Intelligence (UAI) 2024

2023

  1. 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

2021

  1. journal
    On the impact of publicly available news and information transfer to financial markets
    Metod Jazbec, Barna Pàsztor, Felix Faltings, Nino Antulov-Fantulin, and Petter N Kolm
    Royal Society Open Science 2021
  2. 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

2020

  1. AABI
    Factorized Gaussian process variational autoencoders
    Metod Jazbec, Michael Pearce, and Vincent Fortuin
    Symposium on Advances in Approximate Bayesian Inference (AABI) 2020