3 papers
math.OC2026
Convex-Concave Interpolation and Application of PEP to Bilinear-Coupled Saddle-Point Problem
Valery Krivchenko, Alexander Gasnikov, Dmitry Kovalev
The Performance estimation problem (PEP) approach reformulates finding the exact worst-case performance of an algorithm as the solution to an optimization problem. Tractable formul…
math.OC2026
Stronger constraints for smooth min-max games
Valery Krivchenko, Alexander Gasnikov, Dmitry Kovalev
Saddle point problems with smooth convex-concave objective functions are often used to model min-max problems arising in machine learning. First-order methods are the standard para…
math.OC2025
On Solving Minimization and Min-Max Problems by First-Order Methods with Relative Error in Gradients
Artem Vasin, Valery Krivchenko, Dmitry Kovalev +6
First-order methods for minimization and saddle point (min-max) problems are widely used for solving large-scale problems, in particular arising in machine learning. The majority o…