Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex Minimization
math.OC, cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Generalization of Silver Stepsize Schedule to Stochastic Optimization
- Accelerating Stochastic Gradient Method Using Large Stepsize for Smooth Strongly Convex Minimization
- Bias-Optimal Bounds for Stochastic Gradient Descent
- Optimal Linear Decay Learning Rate Schedules and Further Refinements
- A Domain-Specific Harness for End-to-End Automation of Optimization Research
- Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
- Computer-aided analyses of stochastic first-order methods, via interpolation conditions for stochastic 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