Gabriele Cesa

PhD candidate (advised by Max Welling, Arash Behboodi, and Taco Cohen)
AMLab
Institute of Informatics
University of Amsterdam

 

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 and Arash Behboodi. In my research, I study how the geometry of a problem can be encoded into machine learning models to achieve improved data efficiency and generalization, with a particular focus on the task of 3D reconstruction from 2D observations.


Selected Publications

  1. NeurIPS
    On the symmetries of the synchronization problem in Cryo-EM: Multi-Frequency Vector Diffusion Maps on the Projective Plane
    Cesa, Gabriele, Behboodi, Arash, Cohen, Taco, and Welling, Max
    In Conference on Neural Information Processing Systems Dec 2022
  2. NeurIPS
    Generalization Bounds for Equivariant Networks
    Behboodi, Arash, Cesa, Gabriele, and Cohen, Taco
    In Conference on Neural Information Processing Systems Dec 2022
  3. ICLR
    A Program to Build E(N)-Equivariant Steerable CNNs
    Cesa, Gabriele, Lang, Leon, and Weiler, Maurice
    In International Conference on Learning Representations Apr 2022
  4. A data and compute efficient design for limited-resources deep learning
    Mohamed, Mirgahney, Cesa, Gabriele, Cohen, Taco S, and Welling, Max
    ICLR 2020 Workshop on Practical Machine Learning for Developing Countries (PML4DC) Apr 2020
  5. NeurIPS
    General E(2)-Equivariant Steerable CNNs
    Weiler, Maurice, and Cesa, Gabriele
    In Conference on Neural Information Processing Systems Dec 2019