arXiv Machine Learning By Xiangwu Wang, Chengwei Cao, Yicheng Song, Ran Bi, Peilin Yu

Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data

Read the original on arXiv Machine Learning →

arXiv:2607. 06013v1 Announce Type: new Abstract: Adaptive gradient methods can favor max-margin separators that differ from gradient descent, yet a fixed positive numerical stability constant eventually changes the update geometry again.

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