The paper introduces sample-independent and sample-dependent critical lifting between networks of different widths, shows known embeddings do not capture all sample-independent liftings, and proves sample-dependent lifted critical points and saddles exist for sufficiently large sample sizes.
Fukumizu , author S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting
The paper introduces sample-independent and sample-dependent critical lifting between networks of different widths, shows known embeddings do not capture all sample-independent liftings, and proves sample-dependent lifted critical points and saddles exist for sufficiently large sample sizes.