Pedram Akbarian

prof_pic.jpg

I’m a PhD student in Electrical and Computer Engineering department at the University of Texas at Austin, working with Prof. Nhat Ho.

I am interested in scalability and efficiency of large-scale machine learning models, with a specific interest in Mixture-of-Experts, Federated Learning, and Optimization by bridging theory with practical applications.

Prior to UT, I recieved my bachelor’s degree in Electrical and Computer Engineering from University of Tehran, Iran.

selected publications

  1. ICML
    Improving Computational Complexity in Statistical Models with Local Curvature Information
    Pedram Akbarian*, Tongzheng Ren*, Jiacheng Zhuo, Sujay Sanghavi, and Nhat Ho
    In Forty-first International Conference on Machine Learning, 2024
    PDF
  2. ICML
    Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
    Huy Nguyen, Pedram Akbarian, and Nhat Ho
    In Forty-first International Conference on Machine Learning, 2024
    arXiv
  3. ICML
    A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts
    Huy Nguyen, Pedram Akbarian, TrungTin Nguyen, and Nhat Ho
    In Forty-first International Conference on Machine Learning, 2024
    arXiv
  4. ICLR
    Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
    Huy Nguyen, Pedram Akbarian, Fanqi Yan, and Nhat Ho
    In The Twelfth International Conference on Learning Representations, 2024
    arXiv