I am a Ph.D. candidate in Computer Science at Cornell University, where I conduct research in machine learning. My interests include optimization, foundation models, and developing frameworks that bridge theory and practice. I am particularly drawn to complex, unfamiliar problems and the challenge of uncovering the structures that underpin them. I have the privilege of working alongside Sarah Dean, John Thickstun, and Kilian Weinberger.
Prior to this, I pursued a PhD in pure mathematics at Cornell University, where I conducted research on number theory and representation theory under the advisement of Birgit Speh and Ravi Ramakrishna. I completed my undergraduate studies at Sharif University of Technology.
You can find my CV here.
Selected Publications
Lead-Lag Forecasting in social platforms - NeurIPS 2025 (in submission), K. Kazemian*, Z. Liu*, Y. Yang, K. Luo, S. Gu, M. Du, J. Jansons, K. Q Weinberger, J. Thickstun, Y. Yin, S. Dean
Random features approximation for control-affine systems - L4DC 2024, K. Kazemian, Y. Sattar, S. Dean
Datasets for Navigating Sensitive Topics in Preference Data and Recommendations - NeurIPS 2024 Workshop on Safe Generative AI, J. Chee, A. Kovacs, K. Kazemian
Random Features Approximation for Fast Data-Driven Control - NeurIPS Workshop on Gaussian Processes, Dec 2022, K. Kazemian, Sarah Dean
Some Criteria for a Signed Graph to Have Full Rank - Discrete Mathematics, Vol. 343, Issue 8, August 2022, S. Akbari, A. Ghafari, K. Kazemian, M. Nahvi