A particularly challenging problem in AI safety is providing guarantees ...
As machine learning models continue to achieve impressive performance ac...
Deep neural networks have repeatedly been shown to be non-robust to the
...
Uncertainty quantification and robustness to distribution shifts are
imp...
Deep neural networks have emerged as the workhorse for a large section o...
Adversarial training (AT) and its variants have spearheaded progress in
...
The performance of machine learning models can significantly degrade und...
Environments with sparse rewards and long horizons pose a significant
ch...
Deep neural networks (NN) are extensively used for machine learning task...