Cover Image

Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mi, Zhendong, Tan, Qitao, Zhang, Grace Li, Xu, Zhaozhuo, Yuan, Geng, Huang, Shaoyi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning
by: Mi, Zhendong, et al.
Published: (2025)

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
by: Tan, Qitao, et al.
Published: (2025)

OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning
by: Long, Jikai, et al.
Published: (2025)

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning
by: Mi, Zhendong, et al.
Published: (2025)

Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression
by: Zhu, Hengyi, et al.
Published: (2026)

Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training
by: Tan, Qitao, et al.
Published: (2025)

Layer-wise dynamic rank for compressing large language models
by: Mi, Zhendong, et al.
Published: (2025)

Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
by: Ma, Shaocong, et al.
Published: (2025)

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
by: Ran, Yide, et al.
Published: (2025)

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
by: Guo, Wentao, et al.
Published: (2024)

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
by: Sun, Yan, et al.
Published: (2025)

Zeroth-Order Fine-Tuning of LLMs in Random Subspaces
by: Yu, Ziming, et al.
Published: (2024)

HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization
by: Zhao, Huaqin, et al.
Published: (2024)

AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
by: Cai, Zhijie, et al.
Published: (2026)

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation
by: Mi, Zhendong, et al.
Published: (2024)

Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning
by: Seung, Hyunseok, et al.
Published: (2025)

On the Inherent Privacy of Zeroth Order Projected Gradient Descent
by: Gupta, Devansh, et al.
Published: (2025)

Prior-Informed Zeroth-Order Optimization with Adaptive Direction Alignment for Memory-Efficient LLM Fine-Tuning
by: Jin, Feihu, et al.
Published: (2026)

Robust and Efficient Zeroth-Order LLM Fine-Tuning via Adaptive Bayesian Subspace Optimizer
by: Feng, Jian, et al.
Published: (2026)

On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
by: Ma, Shaocong, et al.
Published: (2025)

LLM Zeroth-Order Fine-Tuning is an Inference Workload
by: Li, Zelin, et al.
Published: (2026)

Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization
by: Shu, Yao, et al.
Published: (2026)

Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale
by: Park, Sihwan, et al.
Published: (2025)

Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures
by: Chen, Yiming, et al.
Published: (2024)

Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
by: Shang, Sifeng, et al.
Published: (2025)

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
by: Zhang, Yihua, et al.
Published: (2024)

Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
by: Zhang, Kairun, et al.
Published: (2025)

LLM-NAS: LLM-driven Hardware-Aware Neural Architecture Search
by: Zhu, Hengyi, et al.
Published: (2025)

Private Fine-tuning of Large Language Models with Zeroth-order Optimization
by: Tang, Xinyu, et al.
Published: (2024)

Hi-ZFO: Hierarchical Zeroth- and First-Order LLM Fine-Tuning via Importance-Guided Tensor Selection
by: Jin, Feihu, et al.
Published: (2026)

Obtaining Lower Query Complexities through Lightweight Zeroth-Order Proximal Gradient Algorithms
by: Gu, Bin, et al.
Published: (2024)

The Multi-Query Paradox in Zeroth-Order Optimization
by: Lin, Wei, et al.
Published: (2025)

Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity
by: de Vazelhes, William, et al.
Published: (2022)

FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed
by: Dang, Sizhe, et al.
Published: (2025)

On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization
by: Katti, Prabodh, et al.
Published: (2025)

CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
by: Wang, Shuo, et al.
Published: (2026)

Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
by: Li, Zeman, et al.
Published: (2024)

Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
by: Mi, Zhendong, et al.
Published: (2026)

Zeroth-Order primal-dual Alternating Projection Gradient Algorithms for Nonconvex Minimax Problems with Coupled linear Constraints
by: Zhang, Huiling, et al.
Published: (2024)

On Adaptivity in Zeroth-Order Optimization
by: Dbouk, Hassan, et al.
Published: (2026)