Search Results for author:
Found 4 papers, 3 papers with code
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations
For training from scratch, \textbf{RAMP} achieves SOTA union accuracy of $44. 6\%$ and relatively good clean accuracy of $81. 2\%$ on ResNet-18 against AutoAttack on CIFAR-10.
Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
Further, we propose a novel lightweight aggregation rule, Federated Gradient Projection ($\texttt{FedGP}$), which significantly improves the target performance with domain shift and data scarcity.
EVIDENCEMINER: Textual Evidence Discovery for Life Sciences
EVIDENCEMINER is constructed in a completely automated way without any human effort for training data annotation.
Review and Examination of Input Feature Preparation Methods and Machine Learning Models for Turbulence Modeling
Model extrapolation to unseen flow is one of the biggest challenges facing data-driven turbulence modeling, especially for models with high dimensional inputs that involve many flow features.
Fluid Dynamics Computational Physics
