Arman Bolatov

MS student in Machine Learning at MBZUAI.

prof_pic.jpg

Masdar City

Abu Dhabi, UAE

Hi, I’m Arman. I’m a Master’s student in Machine Learning at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), advised by Eduard Gorbunov, Martin Takáč, and Samuel Horváth.

My research focuses on optimization for machine learning — robust and adaptive methods, federated learning, and the theory behind training deep models. Previously, I earned a BS in Computer Science from Nazarbayev University, where I worked on long-tail learning and gradient-based learning theory with Zhenisbek Assylbekov.

Outside of research, I enjoy competitive math and Kaggle competitions.

selected publications

  1. CPAL
    Byzantine-Robust Optimization under (L_0, L_1)-Smoothness
    Arman Bolatov, Samuel Horváth, Martin Takáč, and 1 more author
    In Conference on Parsimony and Learning (CPAL), Proceedings Track, 2026
  2. Overspecified Mixture Discriminant Analysis: Exponential Convergence, Statistical Guarantees, and Remote Sensing Applications
    Arman Bolatov, Adam Legg, Igor Melnykov, and 3 more authors
    arXiv preprint arXiv:2510.27056, 2025
  3. ECAI
    Long Tail Theory Under Gaussian Mixtures
    Arman Bolatov, Maxat Tezekbayev, Igor Melnykov, and 3 more authors
    In European Conference on Artificial Intelligence (ECAI), 2023