Sample-Adaptive Zeroth-Order Post-Training
cs.LG
Submitted: 2026-10-08
Updated: 2026-10-08
Sources
- Stochastic Optimization with Optimal Importance Sampling
- Online Learning to Sample
- FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed
- On Adaptivity in Zeroth-Order Optimization
- Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Adam: A Method for Stochastic Optimization
- PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training
- Adam with Bandit Sampling for Deep Learning
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Fine-Tuning Language Models with Just Forward Passes
- Stochastic Optimization with Bandit Sampling
- Enhanced Federated Optimization: Adaptive Unbiased Client Sampling with Reduced Variance
- OPT: Open Pre-trained Transformer Language Models
- Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer
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