Many areas of machine learning and science involve large linear algebra
...
A major challenge to out-of-distribution generalization is reliance on
s...
Unlike conventional grid and mesh based methods for solving partial
diff...
While there has been progress in developing non-vacuous generalization b...
Low-precision arithmetic has had a transformative effect on the training...
Probability distributions supported on the simplex enjoy a wide range of...
Scalable Gaussian Process methods are computationally attractive, yet
in...
The Gumbel-Softmax is a continuous distribution over the simplex that is...