Alexander Tyurin

collaborators

3 papers

math.OC2026

Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_{0}, L_{1})$ -Smoothness

Alexander Tyurin

We study first-order methods for convex optimization problems with functions $f$ satisfying the recently proposed $ℓ$ -smoothness condition $||\nabla^{2}f(x)|| \le \ell\left(||\n…

math.OC2026

Optimality in Decentralized Optimization under Bandwidth Constraints

Alexander Tyurin

We consider a realistic decentralized setup with bandwidth-constrained communication and derive optimal time complexities for non-convex stochastic parallel and asynchronous optimi…

math.OC2025

Toward a Unified Theory of Gradient Descent under Generalized Smoothness

Alexander Tyurin

We study the classical optimization problem $min_{x \in R^{d}} f (x)$ and analyze the gradient descent (GD) method in both nonconvex and convex settings. It is well-known th…

Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and (L0​,L1​)-Smoothness

Optimality in Decentralized Optimization under Bandwidth Constraints

Toward a Unified Theory of Gradient Descent under Generalized Smoothness

Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_{0}, L_{1})$ -Smoothness