Saved in:
Bibliographic Details
Main Authors: Deng, Yuyang, Hong, Junyuan, Zhou, Jiayu, Mahdavi, Mehrdad
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.06871
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911792922361856
author Deng, Yuyang
Hong, Junyuan
Zhou, Jiayu
Mahdavi, Mehrdad
author_facet Deng, Yuyang
Hong, Junyuan
Zhou, Jiayu
Mahdavi, Mehrdad
contents Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled dataset affects the generalization of the fine-tuned model is lacking. Existing theoretical research does not adequately account for the heterogeneity of the distribution and tasks in pre-training and fine-tuning stage. To bridge this gap, this paper introduces a novel theoretical framework that illuminates the critical factor influencing the transferability of knowledge acquired during unsupervised pre-training to the subsequent fine-tuning phase, ultimately affecting the generalization capabilities of the fine-tuned model on downstream tasks. We apply our theoretical framework to analyze generalization bound of two distinct scenarios: Context Encoder pre-training with deep neural networks and Masked Autoencoder pre-training with deep transformers, followed by fine-tuning on a binary classification task. Finally, inspired by our findings, we propose a novel regularization method during pre-training to further enhances the generalization of fine-tuned model. Overall, our results contribute to a better understanding of unsupervised pre-training and fine-tuning paradigm, and can shed light on the design of more effective pre-training algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06871
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Generalization Ability of Unsupervised Pretraining
Deng, Yuyang
Hong, Junyuan
Zhou, Jiayu
Mahdavi, Mehrdad
Machine Learning
Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled dataset affects the generalization of the fine-tuned model is lacking. Existing theoretical research does not adequately account for the heterogeneity of the distribution and tasks in pre-training and fine-tuning stage. To bridge this gap, this paper introduces a novel theoretical framework that illuminates the critical factor influencing the transferability of knowledge acquired during unsupervised pre-training to the subsequent fine-tuning phase, ultimately affecting the generalization capabilities of the fine-tuned model on downstream tasks. We apply our theoretical framework to analyze generalization bound of two distinct scenarios: Context Encoder pre-training with deep neural networks and Masked Autoencoder pre-training with deep transformers, followed by fine-tuning on a binary classification task. Finally, inspired by our findings, we propose a novel regularization method during pre-training to further enhances the generalization of fine-tuned model. Overall, our results contribute to a better understanding of unsupervised pre-training and fine-tuning paradigm, and can shed light on the design of more effective pre-training algorithms.
title On the Generalization Ability of Unsupervised Pretraining
topic Machine Learning
url https://arxiv.org/abs/2403.06871