We propose a first-order method for convex optimization, where instead o...
Methods for sequential decision-making are often built upon a foundation...
Most deep learning research has focused on developing new model and trai...
Consider two brands that want to jointly test alternate web experiences ...
Integration of multimodal information from various sources has been show...
Information integration from different modalities is an active area of
r...
Learning distributions over graph-structured data is a challenging task ...
Field observations form the basis of many scientific studies, especially...
Many sequential decision-making systems leverage data collected using pr...
The development of Graph Neural Networks (GNNs) has led to great progres...
Many ecological studies and conservation policies are based on field
obs...
Data augmentation is a popular pre-processing trick to improve generaliz...
Most reinforcement learning methods are based upon the key assumption th...
Most deep neural networks use simple, fixed activation functions, such a...
Most deep neural networks use simple, fixed activation functions, such a...
We present CROSSGRAD, a method to use multi-domain training data to lear...
Augmenting a neural network with memory that can grow without growing th...