CAREER: Theory and Algorithms for Learning with Frozen Pretrained Models

使预先训练的模型适应新的任务和新的数据，对于现代机器学习的民主化至关重要。将大的预先训练好的模型应用于定制任务或新数据是困难的，因为由于原始训练数据的巨大尺寸和不可访问性，不可能对模型进行完全的再训练。训练数据的不可访问性和大小也使传统的领域自适应技术变得不切实际。为了克服这一挑战，已经转向模块化自适应方法，这种方法能够微调“冻结的”预先训练的模型，只需对其内部参数进行最小程度的修改或根本不修改。尽管这些方法在一些实际应用中取得了成功，但对于影响预训练模型精调有效性的因素，理论上的理解还存在差距。该项目开发了一个系统框架，将奠定理论基础并导致严格的微调原则。该项目有可能影响广泛的科学领域和行业，这些领域和行业依赖于适应预先训练的机器学习模型。该项目的更广泛影响包括建立促进STEM的教育倡议，促进现代机器学习未来劳动力的发展。该项目的目标是建立一个统一的理论，并为使用冻结的预训练模型的新兴学习范式设计具有可证明保证的新算法。将建立一个数学框架，以便于对冻结的预训练模型在各种适应和微调方法下的表达能力进行理论分析。该项目将研究三种适应战略：(1)参数高效微调，即更新预先训练的模型的最小部分参数，同时保持其余部分不变；(2)输入/输出处理，涉及修改输入输入或由预先训练的模型产生的输出；(3)模型合成，构建由多个预先训练的模型组成的系统，以处理更复杂的任务。除了分析这些方法，该项目还旨在开发具有可证明的性能保证的新型适应算法。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

Adapting pretrained models to new tasks and new data is crucial for the democratization of modern machine learning. Application of large pretrained models to customized tasks or new data is difficult since full retraining of the model is not possible due to the huge size and inaccesibility of the original training data. The inaccessibility and large size of the training data also renders traditional domain adaptation techniques impractical. To overcome this challenge there has been shift towards modular adaptation methods that enable the fine-tuning of "frozen" pretrained models with minimal or no modifications to their internal parameters. Despite the success of these methods in some practical applications, there is a gap in theoretical understanding of the factors affecting the effectiveness of finetuning of pretrained models. This project develops a systematic framework that will lay theoretical foundations and lead to rigorous fine-tuning principles. The project has the potential to impact a wide range of scientific fields and industries that rely on adaptation of pretrained machine learning models. The project's broader impact includes the establishment of educational initiatives for advancing STEM, contributing to the development of the future workforce in modern machine learning.The project's goal is to establish a unified theory and devise new algorithms with provable guarantees for the emerging paradigm of learning with frozen pretrained models. A mathematical framework will be developed to facilitate the theoretical analysis of the expressive power of frozen pretrained models under various adaptation and fine-tuning methods. The project will investigate three adaptation strategies: (1) parameter-efficient fine-tuning, which updates a minimal portion of the pretrained model's parameters while keeping the rest unchanged; (2) input/output processing, which involves modifying the input entering or the output produced by the pretrained models; and (3) model composition, which constructs a system of multiple pretrained models to address more complex tasks. In addition to analyzing these methods, the project aims to develop novel adaptation algorithms with provable performance guarantees.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.