Search

Bernhard Schölkopf

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
Provably Learning Object-Centric Representations
Jacobian-based Causal Discovery with Nonlinear ICA
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Visual representation learning does not generalize strongly within the same domain
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

Published with Wowchemy — the free, open source website builder that empowers creators.