Pim de Haan
(advised by Max Welling and Taco Cohen)
Institute of Informatics
University of Amsterdam
Science Park 904, C1.234a
I am a PhD student at the Amsterdam Machine Learning Lab (AMLab) with Max Welling and a research associate at Qualcomm AI Research with Taco Cohen. My research interest are about building bridges between geometric deep learning and causality. I’m trying to extend the notions of symmetry used in deep learning to include local symmetries and interventions in causal inference.
Previously, I obtained a masters in theoretical physics from the University of Cambridge and a masters in AI from the University of Amsterdam.
Weakly supervised causal representation learningICLR 2022 Workshop on Objects, Structure and Causality 2022
Gauge equivariant mesh cnns: Anisotropic convolutions on geometric graphsICLR 2021 2021
Mesh convolutional neural networks for wall shear stress estimation in 3D artery modelsIn International Workshop on Statistical Atlases and Computational Models of the Heart 2021
Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous FlowsNeurIPS 2021 workshop on Machine Learning for Physical Systems 2021
Natural graph networksNeurIPS 2020 2020
Reparameterizing Distributions on Lie GroupsAISTATS 2019 (Oral) 2019
Causal confusion in imitation learningNeurIPS 2019 (Oral) 2019
Explorations in Homeomorphic Variational Auto-EncodingIn ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models 2018
Topological Constraints on Homeomorphic Auto-EncodingIn NeurIPS 2018 Workshop on Integration of Deep Learning Theories 2018