160 citations · 263 across the 7 of their papers we have counts for
4 papers · 1 filter
Revisiting the Calibration of Modern Neural Networks
Matthias Minderer, Josip Djolonga, Rob Romijnders +5
Accurate estimation of predictive uncertainty (model calibration) is essential for the safe application of neural networks. Many instances of miscalibration in modern neural networ…
On Mutual Information Maximization for Representation Learning
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein +2
Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different…
Precision-Recall Curves Using Information Divergence Frontiers
Josip Djolonga, Mario Lucic, Marco Cuturi +3
Despite the tremendous progress in the estimation of generative models, the development of tools for diagnosing their failures and assessing their performance has advanced at a muc…
Scalable Variational Inference in Log-supermodular Models
Josip Djolonga, Andreas Krause
We consider the problem of approximate Bayesian inference in log-supermodular models. These models encompass regular pairwise MRFs with binary variables, but allow to capture high-…