MAGDrop: Momentum Adaptive Gradient Dropout With Provable Generalization Guarantees
cs.LG, math.ST, stat.TH
Submitted: 2025-10-21
Updated: 2026-11-03
Code: https://github.com/adeel498/MAGDrop
Terminology
Sources
- Pac-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning
- The Mira-Titan Universe IV. High Precision Power Spectrum Emulation
- Adam: A Method for Stochastic Optimization
- Homoclinic Floer homology via direct limits
- Spin-wave dynamics controlled by tunable ac magnonic crystal
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