Pim de Haan

PhD candidate (advised by Max Welling and Taco Cohen)
AMLab
Institute of Informatics
University of Amsterdam
Science Park 904, C1.234a

 

Personal page   Google scholar   Github   Twitter  

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.


Selected Publications

  1. Weakly supervised causal representation learning
    Brehmer, Johann, De Haan, Pim, Lippe, Phillip, and Cohen, Taco
    ICLR 2022 Workshop on Objects, Structure and Causality 2022
    HTML
  2. Gauge equivariant mesh cnns: Anisotropic convolutions on geometric graphs
    De Haan, Pim, Weiler, Maurice, Cohen, Taco, and Welling, Max
    ICLR 2021 2021
    HTML
  3. Mesh convolutional neural networks for wall shear stress estimation in 3D artery models
    Suk, Julian, Haan, Pim de, Lippe, Phillip, Brune, Christoph, and Wolterink, Jelmer M
    In International Workshop on Statistical Atlases and Computational Models of the Heart 2021
    HTML
  4. Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows
    Haan, Pim, Rainone, Corrado, Cheng, Miranda, and Bondesan, Roberto
    NeurIPS 2021 workshop on Machine Learning for Physical Systems 2021
    HTML
  5. Natural graph networks
    Haan, Pim, Cohen, Taco, and Welling, Max
    NeurIPS 2020 2020
    HTML
  6. Reparameterizing Distributions on Lie Groups
    Falorsi, Luca, Haan, Pim, Davidson, Tim R, and Forré, Patrick
    AISTATS 2019 (Oral) 2019
    HTML
  7. Causal confusion in imitation learning
    De Haan, Pim, Jayaraman, Dinesh, and Levine, Sergey
    NeurIPS 2019 (Oral) 2019
    HTML
  8. Explorations in Homeomorphic Variational Auto-Encoding
    Falorsi, Luca, Haan, Pim, Davidson, Tim R, De Cao, Nicola, Weiler, Maurice, Forré, Patrick, and Cohen, Taco S
    In ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models 2018
    HTML
  9. Topological Constraints on Homeomorphic Auto-Encoding
    Haan, Pim, and Falorsi, Luca
    In NeurIPS 2018 Workshop on Integration of Deep Learning Theories 2018
    HTML