Paul K. Rubenstein — accepted AI-conference papers

2020

On Mutual Information Maximization for Representation Learning

Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic

ICLR 2020poster

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate problems: For example, MI is notoriously hard to estimate, and usin…

Cited by 634 Source ↗code ↗Scholar ↗

2019

The Incomplete Rosetta Stone problem: Identifiability results for Multi-view Nonlinear ICA

Luigi Gresele, Paul K. Rubenstein, Arash Mehrjou, Francesco Locatello, Bernhard Schölkopf

UAI 2019poster

We consider the problem of recovering a common latent source with independent components from multiple views. This applies to settings in which a variable is measured with multiple experimental modalities, and where the goal is to synthesize the disparate measurements into a single unified represent…

Cited by 101 Source ↗PDF ↗Scholar ↗