DPS quantifies deviation of per-sample decision patterns from class averages and shows linear correlation with generalization gaps while unifying degradation scenarios into a continuous trajectory.
Neural computation , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Optimizer choice induces distinct connected regions in the loss landscape of two-layer ReLU networks, with AdamW and Muon sometimes separated by provable barriers.
citing papers explorer
-
Understanding Generalization through Decision Pattern Shift
DPS quantifies deviation of per-sample decision patterns from class averages and shows linear correlation with generalization gaps while unifying degradation scenarios into a continuous trajectory.
-
Optimizer-Induced Mode Connectivity: From AdamW to Muon
Optimizer choice induces distinct connected regions in the loss landscape of two-layer ReLU networks, with AdamW and Muon sometimes separated by provable barriers.