Deep neural networks often fail catastrophically by relying on spurious
...
Effective machine learning models learn both robust features that direct...
Conventional approaches to robustness try to learn a model based on caus...
Training machine learning models robust to distribution shifts is critic...
Supervised learning methods trained with maximum likelihood objectives o...
In this work we introduce a simple baseline for meta-learning. Our
uncon...
Meta-learning is a popular framework for learning with limited data in w...
Despite the advent of deep learning in computer vision, the general
hand...
This paper extends recent work on nonlinear Independent Component Analys...
Meta-learning has proven to be successful at few-shot learning across th...
This paper introduces a new task of politeness transfer which involves
c...
Temporal Point Processes (TPP) with partial likelihoods involving a late...