Search Results for author:
Found 4 papers, 0 papers with code
Pretrain-to-Finetune Adversarial Training via Sample-wise Randomized Smoothing
For certification, we carefully allocate specific robust regions for each test sample.
Optimizing Information Bottleneck in Reinforcement Learning: A Stein Variational Approach
We also show that our method achieves better performance than VIB and mutual information neural estimation (MINE), two other popular approaches to optimize the information bottleneck framework in supervised learning.
Task-Agnostic and Adaptive-Size BERT Compression
NAS-BERT trains a big supernet on a carefully designed search space containing various architectures and outputs multiple compressed models with adaptive sizes and latency.
Visual Attention is Beyond One Single Saliency Map
Under the frequency domain paradigm, we proposed a global inhibition model to mimic this process by suppressing the {\it non-saliency} in the input image; we also show that the dynamic process is influenced by one parameter in the frequency domain.
