A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization
math.OC, cs.CC, cs.LG, cs.NA, math.NA
Submitted: 2025-01-31
Updated: 2026-11-02
Comments: accepted by SIAMOPT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A stochastic smoothing framework for nonconvex-nonconcave minEmax problems with applications to Wasserstein distributionally robust optimization
- On the non-ergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programming
- Huber Loss-Based Penalty Approach to Problems with Linear Constraints
- Developing Lagrangian-based Methods for Nonsmooth Nonconvex Optimization
- Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints
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