HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) face memory challenges due to the high cost of backpropagation. |
| Approach: | They propose a zeroth-order (ZO) optimization that matches memory usage to inference . they propose scalable and memory-efficient zeroth order (ZE) optimizer that integrates annealed A-GNB gradients with diagonal Hessian estimation and layer-wise clipping as a second-order pre-conditioner. |
| Outcome: | The proposed algorithm outperforms state-of-the-art methods with an average speedup of 20 over MeZO on RoBERTa-large and OPT-1.3B. |
Similar Papers
AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in memory-efficient zeroth-order methods have limited their widespread adoption due to performance drops and a high risk of divergence. |
| Approach: | They propose a memory-efficient zeroth-order framework to improve performance and convergence of the MeZO methods by using only forward passes. |
| Outcome: | The proposed framework improves performance and convergence of the proposed methods on Roberta-Large and Llama-2-7B models. |
MUZO: Leveraging Multiple Queries and Momentum for Zeroth-Order Fine-Tuning of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models incur memory overhead due to the need for activation storage for back-propagation (BP). |
| Approach: | They propose a method that estimates gradients through finite differences without activation storage for back-propagation. |
| Outcome: | The proposed method demonstrates superior performance in fine-tuning various LLMs. |
High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing (2026.findings-acl)
Copied to clipboard
| Challenge: | Zeroth-order (ZO) optimization is a memory-efficient alternative to fine-tuning large language models (LLMs). |
| Approach: | They propose a zeroth-order (ZO) optimization framework that offloads model parameters to CPU memory and overlapping transformer block transfer with dual forward computation on a single GPU. |
| Outcome: | The proposed framework achieves a 3x speedup over ZO2 on an OPT-175B model while maintaining memory efficiency and improving training throughput. |
RoZO: Geometry-Aware Zeroth-Order Fine-Tuning on Low-Rank Adapters for Black-Box Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated exceptional performance across a wide range of tasks, yet fine-tuning them efficiently under black-box or memory-constrained settings remains challenging. |
| Approach: | They propose a Riemannian zeroth-order optimization framework that constrains updates to the tangent space of the LoRA manifold. |
| Outcome: | The proposed framework achieves more stable convergence, tighter variance bounds, and superior performance compared to existing ZO methods. |
Global Adaptive Momentum Meets Local Personalized Perturbation: Efficient Federated LLM Fine-Tuning with Zeroth-Order Gradients (2026.acl-long)
Copied to clipboard
| Challenge: | federated fine-tuning of large language models provides privacy-preserving approach to deploying pervasive generative AI services. |
| Approach: | They propose a federated framework for fine-tuning large language models . they propose unified optimization and local personalized perturbation for ZO gradients . |
| Outcome: | The proposed framework outperforms existing methods for integrating ZO gradients in federated learning over diverse heterogeneous data settings. |
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers . fine-timing on resource-constrained edge devices presents significant memory and computational demands . |
| Approach: | They propose a resource-efficient fine-tuning framework for LLMs specifically designed for edge devices. |
| Outcome: | Experiments show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy. |
Hi-ZFO: Hierarchical Zeroth- and First-Order LLM Fine-Tuning via Importance-Guided Tensor Selection (2026.findings-acl)
Copied to clipboard
| Challenge: | generative tasks require a high degree of exploratory capacity, but zeroth-order methods suffer from slow convergence . generative task-specific methods tend to converge toward local minima, causing noise and inefficient estimation . |
| Approach: | They propose a framework that synergizes FO precision with exploratory capability of ZO estimation. |
| Outcome: | The proposed framework synergizes precision of FO gradients with exploratory capability of ZO estimation. |
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models (2025.emnlp-main)
Copied to clipboard
Zhen Zhang, Yifan Yang, Kai Zhen, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang
| Challenge: | Large language models (LLMs) have demonstrated exceptional capabilities across diverse tasks, but their fine-tuning requires significant memory, posing challenges for resource-constrained environments. |
| Approach: | They propose a ZO-based framework that eliminates the need for backpropagation and provides a memory-efficient alternative to backprograming. |
| Outcome: | The proposed framework surpasses first-order methods in performance and accuracy. |
Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prompt optimization is an important technique for adapting Large Language Models (LLMs) to specific tasks. |
| Approach: | They propose a zeroth-order approach which enables efficient prompt tuning solely via inference APIs. |
| Outcome: | The proposed approach outperforms existing black-box prompt tuning methods in terms of performance and convergence speed. |
Memory-Efficient Structured Backpropagation for On-Device LLM Fine-Tuning (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches for fine-tuning large language models require a trade-off between exact gradients with high memory and low memory with noisy estimates (MeZO). |
| Approach: | They propose a method which derivates gradients from LoRA's low-rank structure and manually deriving backward passes to exploit the low-level structure. |
| Outcome: | The proposed method reduces peak memory from 361MB to 136MB for Qwen2.5-0.5B, enabling fine-tuning scenarios previously infeasible on memory-constrained devices. |