3 papers
stat.ML2026
When Kernel Ridge Regression Meets the Hölder-Zygmund Class: Minimax Optimality and Failure of Properness
Yuxuan Hou
We study kernel ridge regression for nonparametric regression over the Hölder-Zygmund class. Using an RKHS equivalent to a Sobolev space of smoothness s+d/2, we prove that misspec…
stat.ML2026
Adversarial Robustness of NTK Neural Networks
Yuxuan Hou
Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversarial robustness of NTK neural…
cs.LG2026
CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence
Yuxuan Hou, Hehe Fan, Jianrong Zhang +6
The automatic synthesis of analog circuits presents significant challenges. Most existing approaches formulate the problem as a single-objective optimization task, overlooking that…