The ubiquitous and demonstrably suboptimal choice of resizing images to ...
Scaling laws have been recently employed to derive compute-optimal model...
We address the problem of unsupervised domain adaptation when the source...
Vision Transformers convert images to sequences by slicing them into pat...
Recent works demonstrate that early layers in a neural network contain u...
The remarkable progress in deep learning in recent years is largely driv...
We propose a novel reduction-to-binary (R2B) approach that enforces
demo...
Fairness and robustness are often considered as orthogonal dimensions wh...
We introduce a new family of techniques to post-process ("wrap") a black...
Recent results suggest that reinitializing a subset of the parameters of...
Summation formulas, such as the Euler-Maclaurin expansion or Gregory's
q...
We study deep neural networks (DNNs) trained on natural image data with
...
Achieving the Bayes optimal binary classification rule subject to group
...
One fundamental goal in any learning algorithm is to mitigate its risk f...
In this paper, a mathematical theory of learning is proposed that has ma...