Accelerated Concatenation of Stepsize Schedules for Smooth Strongly Convex Gradient Descent
math.OC
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/ForeverHaibara/strongly_convex_stepsize_concatenation
Terminology
Sources
- Accelerated Gradient Descent via Long Steps
- A Strengthened Conjecture on the Minimax Optimal Constant Stepsize for Gradient Descent
- Numerical Design of Optimized First-Order Algorithms
- A Domain-Specific Harness for End-to-End Automation of Optimization Research
- A lower bound for stepsize-based acceleration of gradient descent
- Lower Bounds for Anytime Acceleration of Gradient Descent
- Improved Gradient Descent Lower Bounds Beyond Nesterov
- Silver Rate Is (Almost) Optimal for Gradient Descent
- The Grimmer--Shu--Wang Certificate and the Drori--Teboulle Minimax Constant-Stepsize Bound for $N\ge 3$
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