← Search

Andrey Veprikov

2 accepted papers

2026

Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry

AAAI 2026technical

This paper examines a variety of classical optimization problems, including well-known minimization tasks and more general variational inequalities. We consider a stochastic formulation of these problems and, unlike most previous work, we take into account the complex Markov nature of the noise. We

Cited by 0SourcePDFScholar
2026

Softsignum: Smooth Your Signum For Better Heterogeneity Handling

ICML 2026poster

Sign-based optimization methods, such as SignSGD and Signum, have become essential for modern Deep Learning due to their 1) high performance 2) low memory footprint and 3) communication efficiency. Despite their success, these methods suffer from distinct limitations in the terminal phase of trainin…

Cited by 0SourceScholar