Zixi (Charlie) Chen

prof_pic.jpg

I am a Computer Science PhD at NYU Courant, working with Prof. Andrew Gordon Wilson. My research interests include optimization, scaling laws, and structured matrices for efficiently training large neural networks. Prior to this, I finished my Bachelor and Master Degree in Math and Computer Science at NYU, where I worked with Yanjun Han and Stefano Martiniani.

selected publications

  1. hyper_scaling.png
    Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales
    Shikai Qiu*, Zixi Chen*, Hoang Phan, Qi Lei, and Andrew Gordon Wilson
    In Advances in Neural Information Processing Systems (NeurIPS), 2025
  2. einsum_struct.png
    Efficient Linear Layers over a Continuous Space of Structured Matrices
    Andres Potapczynski*, Shikai Qiu*, Marc Finzi, Christopher Ferri, Zixi Chen, Micah Goldblum, Bayan Bruss, Christopher De Sa, and Andrew Gordon Wilson
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
  3. unifying.png
    A unifying approach to self-organizing systems interacting via conservation laws
    Franklin Barrows, Guannan Zhang, Siddhanth Anand, Zixi Chen, Junhan Lin, Akash Desai, Stefano Martiniani, and Francesco Caravelli
    arXiv preprint arXiv:2507.02575, 2025