I am a postdoctoral researcher at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), where I work with Éric Moulines and Eduard Gorbunov. My research focuses on optimization for machine learning, with an emphasis on understanding and improving how large models are trained. I am also interested in distributed and private learning.
I completed my PhD in Computer Science at King Abdullah University of Science and Technology (KAUST), advised by Peter Richtárik. During my PhD, I spent time at Apple and Samsung AI Center (Cambridge, UK), where I worked on heterogeneous, efficient, and personalized federated learning.
Apart from research, I am also passionate about hiking/backpacking, alpine skiing, and rationality.
MS–PhD in Computer Science, 2026
King Abdullah University of Science and Technology (KAUST)
BSc in Applied Mathematics, Computer Science and Physics, 2019
Moscow Institute of Physics and Technology
We provide analysis of the inexact orthogonalized update at Muon’s core, revealing a fundamental coupling between LMO inexactness and optimal step size and momentum.
We propose a general yet simple theorem describing the convergence of SGD under the arbitrary sampling paradigm.