From Imperfect Information to Controlled Steps: Stochastic Optimization under Heavy-Tailed Noise and Compression
math.OC
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness
- Moments and Absolute Moments of the Normal Distribution
- Lower Bounds for Non-Convex Stochastic Optimization
- Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization
- Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees
- High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
- Revisiting the Noise Model of Stochastic Gradient Descent
- Distributed Saddle-Point Problems: Lower Bounds, Near-Optimal and Robust Algorithms
- Decentralized Personalized Federated Learning for Min-Max Problems
- Improving Stochastic Cubic Newton with Momentum
- Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
- A Nesterov-Accelerated Primal-Dual Splitting Algorithm for Convex Nonsmooth Optimization
- Can SGD Handle Heavy-Tailed Noise?
- Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
- Universal fast gradient method for stochastic composit optimization problems
- Second-Order Methods with Cubic Regularization Under Inexact Information
- Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity
- The Ball-Proximal (="Broximal") Point Method: a New Algorithm, Convergence Theory, and Applications
- Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise