← Search

Zhikuan Zhao

2 accepted papers

2022

Certifying Out-of-Domain Generalization for Blackbox Functions

ICML 2022spotlight

Certifying the robustness of model performance under bounded data distribution drifts has recently attracted intensive interest under the umbrella of distributional robustness. However, existing techniques either make strong assumptions on the model class and loss functions that can be certified, su…

2022

Improving Certified Robustness via Statistical Learning with Logical Reasoning

NeurIPS 2022accept

Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification methods are only able to certify under a limited perturbation radius. Given that existing pure data-driven statistical ap…