• Corpus ID: 246485553

Certifying Out-of-Domain Generalization for Blackbox Functions

@inproceedings{Weber2022CertifyingOG,
  title={Certifying Out-of-Domain Generalization for Blackbox Functions},
  author={Maurice Weber and Linyi Li and Boxin Wang and Zhikuan Zhao and Bo Li and Ce Zhang},
  booktitle={ICML},
  year={2022}
}
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, such as smoothness expressed via Lipschitz continuity of gradients, or require to solve complex optimization problems. As a result, the wider application of these techniques is currently lim-ited by… 
On Certifying and Improving Generalization to Unseen Domains
TLDR
This work demonstrates the effectiveness of a universal certification framework based on distributionally robust optimization (DRO) that enables a data-independent evaluation of a DG method complementary to the empirical evaluations on benchmark datasets and proposes a training algorithm that can be used with any DG method to provably improve their certi fied performance.
GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction
TLDR
This paper proposes a physiologically-inspired data augmentation method to improve performance and increase the robustness of heart disease detection based on ECG signals, and designs a ground metric that recognizes theerence betweenECG signals based on physiologically determined features.