AIConfPaper
← Search

Marina Danilova

4 accepted papers

2024

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel Dvurechensky +2
ICML 2024oral

High-probability analysis of stochastic first-order optimization methods under mild assumptions on the noise has been gaining a lot of attention in recent years. Typically, gradient clipping is one of the key algorithmic ingredients to derive good high-probability guarantees when the noise is heavy-…

Cited by 18Source ↗PDF ↗Scholar ↗
2023

High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance

Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel Dvurechensky +2
ICML 2023poster

During the recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimization methods has been growing. One of the main reasons for this is that high-probability complexity bounds are more accurate and less studied than in-expectatio…

Cited by 58Source ↗PDF ↗Scholar ↗
2022

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise

Eduard Gorbunov, Marina Danilova, David Dobre, Pavel Dvurechensky, Alexander Gasnikov, Gauthier Gidel
NeurIPS 2022accept

Stochastic first-order methods such as Stochastic Extragradient (SEG) or Stochastic Gradient Descent-Ascent (SGDA) for solving smooth minimax problems and, more generally, variational inequality problems (VIP) have been gaining a lot of attention in recent years due to the growing popularity of adve…

Cited by 33Source ↗PDF ↗code ↗Scholar ↗
2020

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

Eduard Gorbunov, Marina Danilova, Alexander Gasnikov
NeurIPS 2020poster

In this paper, we propose a new accelerated stochastic first-order method called clipped-SSTM for smooth convex stochastic optimization with heavy-tailed distributed noise in stochastic gradients and derive the first high-probability complexity bounds for this method closing the gap in the theory of…

Cited by 163Source ↗PDF ↗code ↗Scholar ↗