Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening
This work addresses robustness evaluation for neural ODEs, which is incremental as it builds on existing methods for assessing model resilience.
The paper tackles the problem of evaluating robustness in neural ODEs against synthetic distribution shifts by proposing a new accuracy metric and methodology recommendations, and it demonstrates that a cheap data augmentation technique can enhance robustness across multiple datasets.
We investigate the problems and challenges of evaluating the robustness of Differential Equation-based (DE) networks against synthetic distribution shifts. We propose a novel and simple accuracy metric which can be used to evaluate intrinsic robustness and to validate dataset corruption simulators. We also propose methodology recommendations, destined for evaluating the many faces of neural DEs' robustness and for comparing them with their discrete counterparts rigorously. We then use this criteria to evaluate a cheap data augmentation technique as a reliable way for demonstrating the natural robustness of neural ODEs against simulated image corruptions across multiple datasets.