Nurbek Tastan

PhD Candidate in Machine Learning, MBZUAI.

I am Nurbek Tastan, currently pursuing a Doctor of Philosophy degree in Machine Learning. I am associated with the SPriNT-AI lab at MBZUAI, where I conduct my research under the guidance of my supervisor, Dr. Karthik Nandakumar and Dr. Samuel Horvath.

My research focuses on trustworthy federated learning, with particular emphasis on fairness, privacy, efficiency, and robustness in collaborative settings. I also develop methods to make large-scale models, including language models, more efficiently fine-tunable while also preserving utility and user confidentiality.

Passionate about building machine learning systems that are not only performant, but also equitable, privacy-aware, and computationally viable for real-world deployment.

selected publications

  1. CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss
    Nurbek Tastan, and Karthik Nandakumar
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Jun 2023
  2. CPAL
    fedpews-scheme.png
    FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning
    Nurbek Tastan, Samuel Horváth, Martin Takáč, and Karthik Nandakumar
    In The Second Conference on Parsimony and Learning (Proceedings Track) , Mar 2025
  3. Redefining Contributions: Shapley-Driven Federated Learning
    Nurbek Tastan, Samar Fares, Toluwani Aremu, Samuel Horvath, and Karthik Nandakumar
    In International Joint Conference on Artificial Intelligence (IJCAI) , Aug 2024
  4. Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline
    Anas Al-lahham, Muhammad Zaigham Zaheer, Nurbek Tastan, and Karthik Nandakumar
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Jun 2024