Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes
math.OC, cs.LG, stat.ML
Submitted: 2024-12-18
Updated: 2026-11-16
Terminology
Sources
- Accelerating Proximal Gradient Descent via Silver Stepsizes
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
- Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers
- Optimal and parameter-free gradient minimization methods for convex and nonconvex optimization
- Adaptive proximal algorithms for convex optimization under local Lipschitz continuity of the gradient
- Adaptive Gradient Descent without Descent
- Sparse Bilinear Logistic Regression
- AdaBB: Adaptive Barzilai-Borwein Method for Convex 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