Search Results for author:
Found 6 papers, 2 papers with code
Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization
Recently, Sharpness-Aware Minimization (SAM) has shown state-of-the-art performance by seeking flat minima.
Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples
We identify another key factor that influences the performance of certifiable training: \textit{smoothness of the loss landscape}.
Parameter-free HE-friendly Logistic Regression
However, current approaches on the training of encrypted machine learning have relied heavily on hyperparameter selection, which should be avoided owing to the extreme difficulty of conducting validation on encrypted data.
Bridged Adversarial Training
Adversarial robustness is considered as a required property of deep neural networks.
Loss Landscape Matters: Training Certifiably Robust Models with Favorable Loss Landscape
Certifiable training minimizes an upper bound on the worst-case loss over the allowed perturbation, and thus the tightness of the upper bound is an important factor in building certifiably robust models.
Understanding Catastrophic Overfitting in Single-step Adversarial Training
Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed.
