arXiv AI By Yiru Yang, Junling Wang, Nishant Kumar Singh, Luohong Wu, Haoran Yan

Logit Distillation on Manifolds: Mapping by Learning

Read the original on arXiv AI →

arXiv:2606. 00771v1 Announce Type: cross Abstract: A simple way to improve the performance of almost any machine learning model is not to train a single but several models with diverse algorithms which will make slightly distinct kinds of predictions and errors on the same data, and thus improve the average predictions and robustness.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.