Convergence Analysis of SGD under Expected Smoothness
cs.LG
Submitted: 2025-10-23
Updated: 2026-11-08
Terminology
Sources
- Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
- Better Theory for SGD in the Nonconvex World
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates
- Don't Decay the Learning Rate, Increase the Batch Size
- ADADELTA: An Adaptive Learning Rate Method
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis