》  Research Fields

Machine Learning, Statistical Learning Theory, Information Theory

》  Courses

》  Projects

》  Publications

l Paper(论文)

1. Ziqiao Wang and Yongyi Mao. Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States. Conference on Uncertainty in Artificial Intelligence (UAI) 2024.

2. Fanshuang Kong,  Richong Zhang, Ziqiao Wang and Yongyi Mao. On Unsupervised Domain Adaptation: Pseudo Label Guided Mixup for Adversarial Prompt Tuning. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2024.

3. Hailang Huang, Zhijie Nie, Ziqiao Wang and Ziyu Shang. Cross-modal and Uni-modal Soft-label Alignment for Image-Text Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2024.

4. Ziqiao Wang and Yongyi Mao. Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds. Advances in Neural Information Processing Systems (NeurIPS) 2023.

5. Ziqiao Wang and Yongyi Mao. Tighter Information-Theoretic Generalization Bounds from Supersamples. International Conference on Machine Learning (ICML) 2023.

6. Ziqiao Wang and Yongyi Mao. Information-Theoretic Analysis of Unsupervised Domain Adaptation. International Conference on Learning Representations (ICLR) 2023.

7. Zixuan Liu*, Ziqiao Wang* (equal contribution), Hongyu Guo, and Yongyi Mao. Over-Training with Mixup May Hurt Generalization. International Conference on Learning Representations (ICLR) 2023.

8.Ziqiao Wang and Yongyi Mao. On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications. International Conference on Learning Representations (ICLR) 2022.