Here are some of my research works.

Papers

  • DIVA: Dataset Derivative of a Learning Task
    Yonatan Dukler, Alessandro Achille, Giovanni Paolini, Avinash Ravichandran, Marzia Polito, Stefano Soatto.
    Accepted at ICLR 2022 (paper)
    photo
  • Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
    Yonatan Dukler, Quanquan Gu, Guido Montufar.
    In Proceedings of the 37th International Conference on Machine Learning (ICML 2020) (paper)


photo

  • Wasserstein Diffusion Tikhonov Regularization
    Alex T. Lin, Yonatan Dukler, Wuchen Li, Guido Montufar.
    NeurIPS 2019 Workshop on Optimal Transport & Machine Learning (OTML). (paper)


photo


  • A Theory for Undercompressive Shocks in Tears of Wine
    Yonatan Dukler, Hangjie Ji, Claudia Falcon, Andrea L. Bertozzi.
    Physical Review Fluids 5, 034002, 2020 (paper)

photo


  • Wasserstein of Wasserstein loss for learning generative models
    Yonatan Dukler, Wuchen Li, Alex Tong Lin, Guido Montúfar.
    In Proceedings of the 36th International Conference on Machine Learning (ICML 2019). (paper)

photo


  • Automatic valve segmentation in cardiac ultrasound time series data
    Yonatan Dukler, Yurun Ge, Yizhou Qian, Shintaro Yamamoto, Baichuan Yuan, Long Zhao, Andrea L. Bertozzi, Blake Hunter, Rafael Llerena, Jesse T. Yen.
    Proc. SPIE conference on medical imaging, 2018. (paper)

photo

Talks


  • Wasserstein of Wasserstein Loss for Generative Models.
    Invited talk at the Deep Learning Theory Kickoff Meeting at the Max Planck Institute for Mathematics in the Sciences (MiS). Leipzig, Germany.Link

  • Motif Based Graph Convolutional Nets For Network Embeddings and the Planted Clique Problem.
    Spotlight presentation at Algorithms for Threat Detection (ATD) Workshop. Washington DC, USA. Link