GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning
cs.LG, cs.AI
Submitted: 2026-06-01
Updated: 2026-08-29
Comments: Accepted to Findings of EMNLP 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Llama 3 Herd of Models
- Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
- Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- OPT: Open Pre-trained Transformer Language Models
- Tensor-Compressed Back-Propagation-Free Training for (Physics-Informed) Neural Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks