Recently the LARS and LAMB optimizers have been proposed for training ne...
Exoplanet detection with precise radial velocity (RV) observations is
cu...
Selecting an optimizer is a central step in the contemporary deep learni...
In the twilight of Moore's law, GPUs and other specialized hardware
acce...
Increasing the batch size is a popular way to speed up neural network
tr...
Recent hardware developments have made unprecedented amounts of data
par...
Natural language text exhibits hierarchical structure in a variety of
re...