Zebang Shen

ETH Zurich. Post-doctoral researcher

prof_pic.jpg

I am currently a post-doctoral researcher at ETH Zürich, supervised by Prof. Niao He, since the end of 2022. Prior to this role, I was a post-doctoral researcher at the University of Pennsylvania from 2019 to 2022, working under the guidance of Professors Alejandro Ribeiro and Hamed Hassani. I obtained his Bachelor’s degree and Ph.D. in 2014 and 2019, respectively, from Zhejiang University, under the supervision of Prof. Hui Qian.

I am particularly intrigued by the connection between physics and machine learning, and my current research focuses on developing neural network-based methods for solving partial differential equations using entropy dissipation principles. I am also actively involved in optimization in the probability space and stochastic optimization techniques for addressing machine learning problems.

selected publications

  1. Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs
    Zebang Shen ,  and  Zhenfu Wang
    Thirty-seventh Conference on Neural Information Processing Systems, 2023
  2. Self-Consistency of the Fokker Planck Equation
    Zebang Shen ,  Zhenfu Wang ,  Satyen Kale ,  Alejandro Ribeiro ,  Amin Karbasi ,  and  Hamed Hassani
    In Proceedings of Thirty Fifth Conference on Learning Theory , 2022
  3. Sinkhorn barycenter via functional gradient descent
    Zebang Shen ,  Zhenfu Wang ,  Alejandro Ribeiro ,  and  Hamed Hassani
    In Thirty-fifth Conference on Neural Information Processing Systems , 2020
  4. Sinkhorn natural gradient for generative models
    Zebang Shen ,  Zhenfu Wang ,  Alejandro Ribeiro ,  and  Hamed Hassani
    (Spotlight) Advances in Neural Information Processing Systems, 2020
  5. Stochastic conditional gradient++:(non) convex minimization and continuous submodular maximization
    Hamed Hassani ,  Amin Karbasi ,  Aryan Mokhtari ,  and  Zebang Shen
    SIAM Journal on Optimization, 2020
  6. Hessian aided policy gradient
    Zebang Shen ,  Hamed Hassani ,  Chao Mi ,  Hui Qian ,  and  Alejandro Ribeiro
    In International conference on machine learning , 2019