4 papers
Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates
Dmitry Kovalev, Ekaterina Borodich
Recently, several instances of non-Euclidean SGD, including SignSGD, Lion, and Muon, have attracted significant interest from the optimization community due to their practical succ…
Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
Ekaterina Borodich, Dmitry Kovalev
In this paper, we focus on the problem of minimizing a continuously differentiable convex objective function, . Recently, Malitsky (2020); Alacaoglu et al.(2023) devel…
SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
Dmitry Kovalev
In this paper, we revisit stochastic gradient descent (SGD) with AdaGrad-type preconditioning. Our contributions are twofold. First, we develop a unified convergence analysis of SG…
On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms
Dmitry Kovalev, Ekaterina Borodich
We revisit the smooth convex-concave bilinearly-coupled saddle-point problem of the form . In the highly specific case whe…