Alexander Gasnikov

Exponential Objective Decrease in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness

KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems

Generalized Smoothness in Stochastic Convex Optimization: First- and Zero-Order Methods

Simple Stepsizes for Quasi-Newton Methods with Global Convergence Guarantees

Power of Sign: High Probability Bounds Under $(L_0, L_1)$-smoothness and Heavy-Tailed Noise

Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity

OPTAMI: Global Superlinear Convergence of High-order Methods

Decentralized Optimization with Coupled Constraints

On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms

Median Clipping for Zeroth-order Non-Smooth Convex Optimization and Multi Arm Bandit Problem with Heavy-tailed Symmetric Noise

Clipping Improves Adam and AdaGrad when the Noise Is Heavy-Tailed

Decentralized Finite-Sum Optimization over Time-Varying Networks

Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation

Sign Operator for Coping with Heavy-Tailed Noise: High Probability Convergence Bounds with Extensions to Distributed Optimization and Comparison Oracle

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

Adaptive Regularized Newton Methods with Inexact Hessian