MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models
This addresses the challenge of efficient multi-task learning for large language models in settings with limited computational resources, representing a novel application rather than an incremental improvement.
The paper tackles the problem of memory-intensive fine-tuning of large language models in resource-constrained environments by introducing MaZO, a framework for multi-task fine-tuning using zeroth-order optimization, which achieves state-of-the-art performance and surpasses first-order optimization methods.
Large language models have demonstrated exceptional capabilities across diverse tasks, but their fine-tuning demands significant memory, posing challenges for resource-constrained environments. Zeroth-order (ZO) optimization provides a memory-efficient alternative by eliminating the need for backpropagation. However, ZO optimization suffers from high gradient variance, and prior research has largely focused on single-task learning, leaving its application to multi-task learning unexplored. Multi-task learning is crucial for leveraging shared knowledge across tasks to improve generalization, yet it introduces unique challenges under ZO settings, such as amplified gradient variance and collinearity. In this paper, we present MaZO, the first framework specifically designed for multi-task LLM fine-tuning under ZO optimization. MaZO tackles these challenges at the parameter level through two key innovations: a weight importance metric to identify critical parameters and a multi-task weight update mask to selectively update these parameters, reducing the dimensionality of the parameter space and mitigating task conflicts. Experiments demonstrate that MaZO achieves state-of-the-art performance, surpassing even multi-task learning methods designed for first-order optimization.