For 2-layer homogeneous NNs on multi-index models, flattest interpolators achieve low population loss when data is a sum of single-index models with low approximation error and label noise.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Flatness and Generalization: Learning Multi-Index Models with Homogeneous Neural Networks
For 2-layer homogeneous NNs on multi-index models, flattest interpolators achieve low population loss when data is a sum of single-index models with low approximation error and label noise.