Anytime-Valid Confidence Sequences for Consistent Uncertainty Estimation in Early-Exit Neural Networks

1 code implementation • 10 Nov 2023 • Metod Jazbec, Patrick Forré, Stephan Mandt, Dan Zhang, Eric Nalisnick

Early-exit neural networks (EENNs) facilitate adaptive inference by producing predictions at multiple stages of the forward pass.

Conformal Prediction Uncertainty Quantification +1

Factorized Gaussian Process Variational Autoencoders

1 code implementation • pproximateinference AABI Symposium 2021 • Metod Jazbec, Michael Pearce, Vincent Fortuin

Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency across latent variables.

Scalable Gaussian Process Variational Autoencoders

1 code implementation • 26 Oct 2020 • Metod Jazbec, Matthew Ashman, Vincent Fortuin, Michael Pearce, Stephan Mandt, Gunnar Rätsch

Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors.

On the impact of publicly available news and information transfer to financial markets

1 code implementation • 22 Oct 2020 • Metod Jazbec, Barna Pásztor, Felix Faltings, Nino Antulov-Fantulin, Petter N. Kolm

We quantify the propagation and absorption of large-scale publicly available news articles from the World Wide Web to financial markets.