Showing stat.MLShow all
2 papers · 1 filter
stat.ML2022
Rethinking Sharpness-Aware Minimization as Variational Inference
Szilvia Ujváry, Zsigmond Telek, Anna Kerekes +2
Sharpness-aware minimization (SAM) aims to improve the generalisation of gradient-based learning by seeking out flat minima. In this work, we establish connections between SAM and…
stat.ML2021
Depth Without the Magic: Inductive Bias of Natural Gradient Descent
Anna Kerekes, Anna Mészáros, Ferenc Huszár
In gradient descent, changing how we parametrize the model can lead to drastically different optimization trajectories, giving rise to a surprising range of meaningful inductive bi…