An Adaptive Short-Step Variant of BroxGD with Linear Convergence under Quadratic Growth
math.OC
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Convergence Guarantees for the Broximal Point Method under Perturbations
- A Whole New Ball Game: A Primal Accelerated Method for Matrix Games and Minimizing the Maximum of Smooth Functions
- Error bounds, quadratic growth, and linear convergence of proximal methods
- Lower Bounds for Linear Minimization Oracle Methods Optimizing over Strongly Convex Sets
- Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
- Broximal Alignment for Global Non-Convex Optimization
- Lower Bounds for Frank-Wolfe on Strongly Convex Sets
- A Linearly Convergent Projection-Free Algorithm for Smooth Convex Sets
- Restarting Frank-Wolfe: Faster Rates Under H\"olderian Error Bounds
- On the Global Linear Convergence of Frank-Wolfe Optimization Variants
- Stabilized Proximal Point Method via Trust Region Control
- Local LMO is Secretly a Projection Method!
- Frank-Wolfe is Approximate Broximal Gradient Descent
- Broximal Gradient Descent: A Projection-Free Sister of Projected Gradient Descent
- Avoiding bad steps in Frank Wolfe variants
- Fast Frank--Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
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