A. Agafonov

activity

20192026

most citedFLECS: A Federated Learning Second-Order Framework via Compression and Sketching

3 citations · 10 across the 14 of their papers we have counts for

collaborators

Showing 2023 · math.OCShow all

2 papers · 2 filters

math.OC2023★ 1 cited

Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness

Artem Agafonov, Dmitry Kamzolov, Alexander Gasnikov +4

We present a new accelerated stochastic second-order method that is robust to both gradient and Hessian inexactness, which occurs typically in machine learning. We establish theore…

math.OC2023

Cubic Regularization is the Key! The First Accelerated Quasi-Newton Method with a Global Convergence Rate of $O (k^{- 2})$ for Convex Functions

Dmitry Kamzolov, Klea Ziu, Artem Agafonov +1

In this paper, we propose the first Quasi-Newton method with a global convergence rate of $O (k^{- 1})$ for general convex functions. Quasi-Newton methods, such as BFGS, SR-1, are we…

Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness

Cubic Regularization is the Key! The First Accelerated Quasi-Newton Method with a Global Convergence Rate of O(k−2) for Convex Functions

Cubic Regularization is the Key! The First Accelerated Quasi-Newton Method with a Global Convergence Rate of $O (k^{- 2})$ for Convex Functions