Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
cs.LG, math.OC
Submitted: 2026-05-14
Updated: 2026-11-12
Terminology
Sources
- Towards Weaker Variance Assumptions for Stochastic Optimization
- Lower Bounds and Proximally Anchored SGD for Non-Convex Minimization Under Unbounded Variance
- Accelerated stochastic approximation with state-dependent noise
- SpiderBoost and Momentum: Faster Stochastic Variance Reduction Algorithms
- Why gradient clipping accelerates training: A theoretical justification for adaptivity
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