Stepsize modulation for cross entropy from local quadratic optimization
cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/Brbauwens/adaptive_stepsize_modular
Terminology
Sources
- Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
- New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results
- An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes
- Barzilai-Borwein Step Size for Stochastic Gradient Descent
- A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima
- SGD Converges to Global Minimum in Deep Learning via Star-convex Path
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