My research interests lie at the intersection of optimization and machine learning, with a particular focus on federated learning and communication-efficient distributed algorithms. I have contributed to multiple publications at top-tier conferences including NeurIPS and ICML. Additionally, I serve as a reviewer for TMLR and major machine learning conferences, including NeurIPS, ICML, and ICLR.

Areas of expertise: stochastic and distributed optimization for ML; communication-efficient methods for federated learning (compression, quantization, local updates, error feedback); variance reduction; convex/non-convex and smooth/non-smooth convergence analysis; orthogonalized gradient preconditioning; reproducible large-scale numerical experiments.