activity
20242026
collaborators
Showing math.OCShow all

5 papers · 1 filter

math.OC2026

Lower Bounds for Anytime Acceleration of Gradient Descent

Chung-En Tsai, Ilyas Fatkhullin, Liang Zhang +1

Recent work suggests that the convergence rate of gradient descent (GD) in smooth convex optimization can be significantly improved by employing large stepsizes that may violate th…

math.OC2025

Global Solutions to Non-Convex Functional Constrained Problems with Hidden Convexity

Ilyas Fatkhullin, Niao He, Guanghui Lan +1

Constrained non-convex optimization is fundamentally challenging, as global solutions are generally intractable and constraint qualifications may not hold. However, in many applica…

math.OC2025

Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits

Abdurakhmon Sadiev, Peter Richtárik, Ilyas Fatkhullin

Heavy-tailed noise is pervasive in modern machine learning applications, arising from data heterogeneity, outliers, and non-stationary stochastic environments. While second-order m…

math.OC2025

Can SGD Handle Heavy-Tailed Noise?

Ilyas Fatkhullin, Florian Hübler, Guanghui Lan

Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- common in modern machine learning and reinf…

math.OC2024

From Gradient Clipping to Normalization for Heavy Tailed SGD

Florian Hübler, Ilyas Fatkhullin, Niao He

Recent empirical evidence indicates that many machine learning applications involve heavy-tailed gradient noise, which challenges the standard assumptions of bounded variance in st…