3 papers
cs.LG2026
A Bifurcation Theory Framework for Gradient Descent on the Edge of Stability
Eric Gan
The Edge of Stability (EoS) phenomenon, where gradient descent operates with sharpness exceeding the classical convergence threshold yet the loss decreases over long timescales, is…
cs.LG2026
Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
Eric Gan
Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence anal…
cs.LG2026
Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
Dang Nguyen, Paymon Haddad, Eric Gan +1
Can we modify the training data distribution to encourage the underlying optimization method toward finding solutions with superior generalization performance on in-distribution da…