Beznosikov Aleksandr Nikolaevich

Publications in Math-Net.Ru

1. Optimization with Markovian noise: towards optimal rates in strong growth case
   
   Dokl. RAN. Math. Inf. Proc. Upr., 527 (2025),  523–532
2. Extrasaga: variance reduction hybrid method for variational inequalities
   
   Dokl. RAN. Math. Inf. Proc. Upr., 527 (2025),  415–431
3. Sampling of semi-orthogonal matrices for the Muon algorithm
   
   Dokl. RAN. Math. Inf. Proc. Upr., 527 (2025),  217–228
4. Communication-efficient solution of distributed variational inequalities using biased compression, data similarity and local updates
   
   Computer Research and Modeling, 16:7 (2024),  1813–1827
5. Zero order algorithm for decentralised optimization problems
   
   Dokl. RAN. Math. Inf. Proc. Upr., 520:2 (2024),  295–312
6. Local methods with adaptivity via scaling
   
   Uspekhi Mat. Nauk, 79:6(480) (2024),  117–158
7. Local SGD for near-quadratic problems: Improving convergence under unconstrained noise conditions
   
   Uspekhi Mat. Nauk, 79:6(480) (2024),  83–116
8. Accelerated Stochastic ExtraGradient: Mixing Hessian and gradient similarity to reduce communication in distributed and federated learning
   
   Uspekhi Mat. Nauk, 79:6(480) (2024),  5–38
9. Effective method with compression for distributed and federated cocoercive variational inequalities
   
   Proceedings of ISP RAS, 36:5 (2024),  93–108
10. On some works of Boris Teodorovich Polyak on the convergence of gradient methods and their development
    
    Zh. Vychisl. Mat. Mat. Fiz., 64:4 (2024),  587–626
11. Optimal data splitting in distributed optimization for machine learning
    
    Dokl. RAN. Math. Inf. Proc. Upr., 514:2 (2023),  343–354
12. Optimal analysis of method with batching for monotone stochastic finite-sum variational inequalities
    
    Dokl. RAN. Math. Inf. Proc. Upr., 514:2 (2023),  212–224
13. Activations and gradients compression for model-parallel training
    
    Dokl. RAN. Math. Inf. Proc. Upr., 514:2 (2023),  126–137
14. A unified analysis of variational inequality methods: variance reduction, sampling, quantization, and coordinate descent
    
    Zh. Vychisl. Mat. Mat. Fiz., 63:2 (2023),  189–217
15. Linearly convergent gradient-free methods for minimization of parabolic approximation
    
    Computer Research and Modeling, 14:2 (2022),  239–255


16. Defending against Byzantine attacks by trust-based weighting of agents
    
    Uspekhi Mat. Nauk, 80:6(486) (2025),  191–194