Hossein Taheri

I am a Postdoctoral Scholar in the Department of Computer Science and Engineering at UC San Diego, working with Arya Mazumdar. Previously, I obtained my Ph.D. in Electrical and Computer Engineering from UC Santa Barbara, where I was advised by Christos Thrampoulidis. I completed my B.Sc. in Electrical Engineering and Mathematics (double major) at Sharif University of Technology.

Research Interests

• Deep Learning Theory, Generalization and Optimization of Neural Networks
• Transformers and in-context learning
• Continual Learning
• Distributed Optimization
• High-dimensional Statistics

Publications

Ph.D. Thesis:

1. Generalization and Optimization in the Interpolation Regime: From Linear Models to Neural Networks [link]
   H. Taheri, University of California, Santa Barbara, 2024 .

   Preprints:

   2. On the Theory of Continual Learning with Gradient Descent for Neural Networks [link]
      H. Taheri, A. Ghosh, A. Mazumdar (Preprint).

   Peer-Reviewed Publications:

   3. Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods [link]
      H. Taheri, C. Thrampoulidis, A. Mazumdar (ICLR 2025).
   4. Generalization and Stability of Interpolating Neural Networks with Minimal Width [link]
      H. Taheri, C. Thrampoulidis (JMLR 2024).
   5. On the Optimization and Generalization of Multi-head Attention [link]
      P. Deora*, R. Ghaderi*, H. Taheri*, C. Thrampoulidis (TMLR 2024 and selected for poster presentation at ICLR 2025).
   6. On Generalization of Decentralized Learning with Separable Data [link]
      H. Taheri, C. Thrampoulidis (AISTATS 2023).
   7. Fast Convergence in Learning Two-layer Neural Networks with Separable Data [link]
      H. Taheri, C. Thrampoulidis (AAAI 2023).
   8. Asymptotic Behavior of Adversarial Training in Binary Linear Classification [link]
      H. Taheri, R. Pedarsani, C. Thrampoulidis (IEEE TNNLS 2023).
   9. Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions [link]
      H. Taheri, R. Pedarsani, C. Thrampoulidis (AISTATS 2021).
   10. Quantized Decentralized Stochastic Learning over Directed Graphs [link]
       H. Taheri, A. Mokhtari, H. Hassani, R. Pedarsani (ICML 2020).
   11. Sharp Asymptotics and Optimal Performance for Inference in Binary Models [link]
       H. Taheri, R. Pedarsani, C. Thrampoulidis (AISTATS 2020).
   12. Robust and Communication-efficient Collaborative Learning [link]
       A. Reisizadeh, H. Taheri, A. Mokhtari, H. Hassani, R. Pedarsani (NeurIPS 2019).

   Other Publications:

   13. Asymptotic Behavior of Adversarial Training in Binary Linear Classification[link]
       H. Taheri, R. Pedarsani, C. Thrampoulidis (ISIT 2022).
   14. Sharp Guarantees and Optimal Performance for Inference in Binary and Gaussian-mixture Models[link]
       H. Taheri, R. Pedarsani, C. Thrampoulidis (Entropy, 2021).
   15. Optimality of Least-squares for Classification in Gaussian Mixture Models[link]
       H. Taheri, R. Pedarsani, C. Thrampoulidis (ISIT 2020).
   16. Sharp Guarantees for Solving Random Equations with One-bit Information[link]
       H. Taheri, R. Pedarsani, C. Thrampoulidis (Allerton 2019).

Academic Experience