Sim2Real domain adaptation (DA) research focuses on the constrained sett...
Calibration is a fundamental property of a good predictive model: it req...
Modern deep learning systems require huge data sets to achieve impressiv...
Given a small training data set and a learning algorithm, how much more ...
Modern computer vision applications rely on learning-based perception mo...
Linear interpolation between initial neural network parameters and conve...
Existing approaches to few-shot learning deal with tasks that have
persi...
Machine learning models have traditionally been developed under the
assu...
Our understanding of learning input-output relationships with neural net...
Posterior collapse in Variational Autoencoders (VAEs) arises when the
va...
Lipschitz constraints under L2 norm on deep neural networks are useful f...
The vast majority of successful deep neural networks are trained using
v...
Training neural networks subject to a Lipschitz constraint is useful for...
Bayesian neural networks (BNNs) allow us to reason about uncertainty in ...
Momentum is a simple and widely used trick which allows gradient-based
o...