Search Results for author:
Found 3 papers, 0 papers with code
Enhancing Certified Robustness of Smoothed Classifiers via Weighted Model Ensembling
Moreover, SWEEN models constructed using a few small models can achieve comparable performance to a single large model with a notable reduction in training time.
RODE-Net: Learning Ordinary Differential Equations with Randomness from Data
To train the RODE-Net, we first estimate the parameters of the unknown RODE using the symbolic networks \cite{long2019pde} by solving a set of deterministic inverse problems based on the measured data, and use a generative adversarial network (GAN) to estimate the true distribution of the RODE's parameters.
Enhancing Certified Robustness via Smoothed Weighted Ensembling
Moreover, SWEEN models constructed using a few small models can achieve comparable performance to a single large model with a notable reduction in training time.
