Wanda-Guided Sparse Perturbations for Efficient Zeroth-Order Optimization
cs.LG, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
- The Llama 3 Herd of Models
- On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
- AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
- Qwen2.5 Technical Report
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