Pedram Akbarian
Email | GitHub | LinkedIn | Google Scholar
Email: akbarian@utexas.edu
I’m a Ph.D. student in the Electrical and Computer Engineering Department at the University of Texas at Austin, advised by Prof. Nhat Ho and Prof. Atlas Wang. I’m broadly interested in the theoretical and practical aspects of modern machine learning, with a focus on understanding the fundamental principles of designing and training scalable and efficient foundation models.
In Summer 2026, I was a Quantitative Research Intern at Point72. Previously, I was an AI Research Intern at Toyota InfoTech Labs.
Before joining UT Austin, I earned my B.Sc. in Electrical Engineering with a minor in Computer Engineering from the University of Tehran, Iran. See my CV for more details.
selected publications
- PreprintSigmoid Self-Attention is Better than Softmax Self-Attention: A Mixture-of-Experts PerspectivearXiv:2502.00281, 2025Under review
- PreprintQuadratic Gating Functions in Mixture of Experts: A Statistical InsightarXiv:2410.11222, 2024Under review
- ICLRStatistical Advantages of Perturbing Cosine Router in Sparse Mixture of ExpertsIn International Conference on Learning Representations (ICLR), 2025
- ICMLImproving Computational Complexity in Statistical Models with Local Curvature InformationIn International Conference on Machine Learning (ICML), 2024
- ICMLIs Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?In International Conference on Machine Learning (ICML), 2024
- ICMLA General Theory for Softmax Gating Multinomial Logistic Mixture of ExpertsIn International Conference on Machine Learning (ICML), 2024
- ICLRStatistical Perspective of Top-K Sparse Softmax Gating Mixture of ExpertsIn International Conference on Learning Representations (ICLR), 2024