A linear stability analysis introduces data coherence to explain why SGD and SAM prefer stable and simple minima in two-layer ReLU networks.
This can be seen as a form of simplicity bias (since a max-margin separator in linear space is a simpler decision boundary than a complex wiggle that also separates the data)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
A linear stability analysis introduces data coherence to explain why SGD and SAM prefer stable and simple minima in two-layer ReLU networks.