Message passing neural networks have shown a lot of success on
graph-str...
Data augmentation (DA) is a powerful workhorse for bolstering performanc...
Heavy Ball (HB) nowadays is one of the most popular momentum methods in
...
Meaningful and simplified representations of neural activity can yield
i...
Stochastic gradient descent (SGD) with stochastic momentum is popular in...
State-of-the-art methods for self-supervised learning (SSL) build
repres...
Optimal transport (OT) is a widely used technique for distribution align...
Most existing black-box optimization methods assume that all variables i...