Nikita Kornilov

activity

20232026

most citedAccelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

3 citations · 4 across the 8 of their papers we have counts for

collaborators

Showing 2025Show all

2 papers · 1 filter

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…

math.OC2025

Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_{0}, L_{1})$ -Smoothness

Nikita Kornilov, Philip Zmushko, Andrei Semenov +3

In recent years, non-convex optimization problems are more often described by generalized $(L_{0}, L_{1})$ -smoothness assumption rather than standard one. Meanwhile, severely corrupted…

On Solving Minimization and Min-Max Problems by First-Order Methods with Relative Error in Gradients

Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under (L0​,L1​)-Smoothness

Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_{0}, L_{1})$ -Smoothness