We abstract the features (i.e. learned representations) of multi-modal d...
Recent progress was made in characterizing the generalization error of
g...
Deep neural networks are known to be vulnerable to unseen data: they may...
Studies on benign overfitting provide insights for the success of
overpa...
Benign overfitting demonstrates that overparameterized models can perfor...
Generalization is one of the critical issues in machine learning. Howeve...
It is challenging to deal with censored data, where we only have access ...
Due to its strong interpretability, linear regression is widely used in
...