Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
cs.LG, math.OC
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/nizswan/Zeroth-First-Order-Framework
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Demystifying the Myths and Legends of Nonconvex Convergence of SGD
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- The Llama 3 Herd of Models
- Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization
- Zeroth-Order Optimization is Secretly Single-Step Policy Optimization
- Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
- Overtrained Language Models Are Harder to Fine-Tune
- On the optimization dynamics of RLVR: Gradient gap and step size thresholds
- Gemma 2: Improving Open Language Models at a Practical Size
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks