3 papers
stat.ML2026
The Noise Premium in Adversarial Training for Kernel Regression
Yiling Xie, Xiaoming Huo
Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency. We study this trade-off in kernel regres…
cs.AI2026
Utility-Aware Multimodal Contrastive Learning for Product Image Generation
Xiaohang Feng, Yiling Xie
Product images strongly influence consumer decision-making in online marketplaces. Empowered by multimodal contrastive learning, generative AI can output images that closely align…
math.ST2024
High-dimensional (Group) Adversarial Training in Linear Regression
Yiling Xie, Xiaoming Huo
Adversarial training can achieve robustness against adversarial perturbations and has been widely used in machine learning models. This paper delivers a non-asymptotic consistency…