专为微调收敛模型设计的优化器，提升新任务表现
PROFIT: A Specialized Optimizer for Deep Fine Tuning
- 基于收敛模型特性，通过梯度正交化引导优化
- 在图像分类、多模态训练等任务中超越传统方法
- 模块化设计，可无缝接入任意训练流程
预训练模型的微调在生成式AI、计算机视觉和机器人领域已成常态。尽管已有大量工作致力于提升微调效率，但针对提升微调后模型性能的研究仍较少。为此，我们提出PROFIT，首个专为增量微调收敛模型而设计的优化器，适用于新任务或新数据集。与SGD或Adam等传统优化器不同，PROFIT显式考虑收敛模型的特性以正则化优化过程。通过时间梯度正交化机制，PROFIT在图像分类、多模态语言模型训练及大规模运动预测等多种任务中均表现更优。此外，PROFIT被封装为模块化优化器，可直接集成至任意训练流程，工程成本极低。
原文摘要 · Abstract (English)
The fine-tuning of pre-trained models has become ubiquitous in generative AI, computer vision, and robotics. Although much attention has been paid to improving the efficiency of fine-tuning model, there has been less scholarship around fine-tuning specifically for improved model performance. To remedy this gap, we present PROFIT, one of the first optimizers designed to incrementally fine-tune converged models on new tasks and/or datasets. Unlike traditional optimizers such as SGD or Adam, which make minimal assumptions due to random initializations, PROFIT takes the properties of a converged model into account explicitly to regularize the optimization process. Employing a temporal gradient-orthogonalization process, PROFIT outperforms fine-tuning methods in various tasks, from image classification to multimodal language model training to large-scale motion prediction. Moreover, PROFIT is encapsulated as a modular optimizer, which makes it easy to integrate directly into any training pipeline with minimal engineering effort.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。