Neural network interactions that generalize follow a decay-shaped distribution over complexity, while non-generalizing interactions follow a spindle-shaped distribution, which a four-parameter fit can separate.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Revisiting Generalization Power of a DNN in Terms of Symbolic Interactions
Neural network interactions that generalize follow a decay-shaped distribution over complexity, while non-generalizing interactions follow a spindle-shaped distribution, which a four-parameter fit can separate.