On the Complexity of Finding Stationary Points in Stochastic (L 0, L 1) -Smooth Nonconvex Optimization
math.OC
Submitted: 2026-10-15
Updated: 2026-11-15
Terminology
Sources
- Stability and Generalization of Stochastic Nonconvex Optimization under Heavy-Tailed Noise: From Gradient Norm to Goldstein Stationarity
- High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and (L 0,L 1) -Smoothness
- Complexity of normalized stochastic first-order methods with momentum under heavy-tailed noise
- Decentralized Relaxed Smooth Optimization with Gradient Descent Methods
- Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum
- Problem-Parameter-Free Decentralized Nonconvex Stochastic Optimization
- Stochastic Bilevel Optimization with Heavy-Tailed Noise
- Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation
- Linear Convergence Rate in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness
- High Probability Convergence of Clipped-SGD Under Heavy-tailed Noise
- Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
- Revisiting Stochastic Proximal Point Methods: Generalized Smoothness and Similarity
- Near-Optimal Decentralized Stochastic Nonconvex Optimization with Heavy-Tailed Noise
- Optimal Asynchronous Stochastic Nonconvex Optimization under Heavy-Tailed Noise
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