The impressive generalization performance of modern neural networks is
a...
We propose a metric – Projection Norm – to predict a model's performance...
Adversarially trained models exhibit a large generalization gap: they ca...
Recent work showed that there could be a large gap between the classical...
The classical bias-variance trade-off predicts that bias decreases and
v...
Web services are widely used in many areas via callable APIs, however, d...
This paper considers the fundamental problem of learning a complete
(ort...