Google Scholar
Education
Ph.D., Biomedical Engineering, Carnegie Mellon University 2015
M.Sc., Electrical and Computer Engineering, Colorado State University, 2012
B.Sc., Electrical Engineering, Sharif University of Technology, 2010
About
Soheil Kolouri is an Assistant Professor in the Department of Computer Science at Vanderbilt University. He directs the Machine Intelligence and Neural Technologies (MINT) Laboratory, where his group works on mathematical machine learning, computational optimal transport, continual representation learning, generative modeling, and model compression. Before joining Vanderbilt in Fall 2021, he was a Research Scientist and Principal Investigator at HRL Laboratories in Malibu, California, where he led and co-led several large DARPA programs, including Lifelong Learning Machines and Learning with Less Labels. He earned his Ph.D. in Biomedical Engineering from Carnegie Mellon University in 2015, with a focus on machine learning for medical image analysis. At Carnegie Mellon, he received the Bertucci Fellowship Award from the College of Engineering in 2014 and the Outstanding Dissertation Award from the Biomedical Engineering Department in 2015. He received an NSF CAREER Award in 2024 for advancing Optimal Transport beyond probability measures for robust geometric representation learning. His work has also been recognized with international honors, including the Best Paper Award at IEEE ICASSP 2023.
Research Focus
Mathematical Machine Learning, Computational Optimal Transport, Representation Learning, Generative Modeling, and Scalable and Efficient Machine Learning
Publications Highlight
1. Abbasi, A., Thrash, C., Qin, H., Sharma, S., Seifi, S., & Kolouri, S. (2026). Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression. In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026). https://icml.cc/virtual/2026/poster/61159
2. Liu, X., Bai, Y., Díaz Martín, R., Shi, K., Shahbazi, A., Landman, B. A., Chang, C., & Kolouri, S. (2025). Linear spherical sliced optimal transport: A fast metric for comparing spherical data. In Proceedings of the International Conference on Learning Representations (ICLR 2025, Spotlight). https://proceedings.iclr.cc/paper_files/paper/2025/file/cc10fd7fe3e0d2af517cedf99fbc0651-Paper-Conference.pdf
3. Shahbazi, A., Akbari, E., Salehi, D., Liu, X., Naderializadeh, N., & Kolouri, S. (2025). ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans. In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025). https://openreview.net/pdf?id=Uq70mJuUB8