题目：Unsupervised Transfer Learning via Adversarial Contrastive Training

内容简介：Learning a data representation for downstream supervised learning tasks under unlabeled scenario is both critical and challenging. In this paper, we propose a novel unsupervised transfer learning approach using adversarial contrastive training (ACT). Our experimental results demonstrate outstanding classification accuracy with both fine-tuned linear probe and K-NN protocol across various datasets, showing competitiveness with existing state-of-the-art self-supervised learning methods. Moreover, we provide an end-to-end theoretical guarantee for downstream classification tasks in a misspecified, over-parameterized setting, highlighting how a large amount of unlabeled data contributes to prediction accuracy. Our theoretical findings suggest that the testing error of downstream tasks depends solely on the efficiency of data augmentation used in ACT when the unlabeled sample size is sufficiently large. This offers a theoretical understanding of learning downstream tasks with a small sample size.

报告人：焦雨领

报告人简介：武汉大学人工智能学院，教授博导，副院长。入选国家高层次青年人才，主要研究机器学习、科学计算。近期关注深度学习数理基础，在计算数学、应用数学、统计学、电子工程、人工智能等领域的旗舰期刊和会议上发表论文三十多篇：SIAM 系列（5 篇）、Appl.Comput. Harmon. Anal.(2篇)、Inverse Probl. (2 篇)；Ann. Stat. （3 篇）、J.Amer. Statist. Assoc.； IEEE Trans. Inf. Theory (3 篇)、IEEE Trans. Signal Process.（3篇）；J. Mach. Learn. Res. (6 篇)、ICML (3 篇)、NeurIPS (3篇，其中一篇Oral、一篇Spotlight)；Nat. Commun.。主持国家重点研发计划子课题、国家自然科学基金面上项目及一批同华为开展的校企合作项目。

时  间：2025年4月4日（周五）上午09:30开始

地  点：腾讯会议： 486-526-378

热烈欢迎广大师生参加!

 信息科学技术学院

2025年4月2日