3 papers
cs.LG2026
On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
Yue Zhang, Zhiyi Dong, Tommaso Cesari +1
We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain rule that generates intermedia…
stat.ML2025
On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
Zhiyi Dong, Zixuan Liu, Yongyi Mao
This paper studies the hardness of unsupervised domain adaptation (UDA) under covariate shift. We model the uncertainty that the learner faces by a distribution in the ground-…
cs.LG2025
Adversarial Defenses via Vector Quantization
Zhiyi Dong, Yongyi Mao
Adversarial attacks pose significant challenges to the robustness of modern deep neural networks in computer vision, and defending these networks against adversarial attacks has at…