A short note arguing via Minkowski sums that infinite-width shallow network objectives become convex in the limit, while leaving the finite-width local landscape unproved.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Asymptotic convexity of wide and shallow neural networks
A short note arguing via Minkowski sums that infinite-width shallow network objectives become convex in the limit, while leaving the finite-width local landscape unproved.