Neural networks approximate low-variation regions of a function first, and a preprocessing trick that subtracts an interpolant speeds up training, per the paper's 'value change' analysis.
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
-
Objective Value Change and Shape-Based Accelerated Optimization for the Neural Network Approximation
Neural networks approximate low-variation regions of a function first, and a preprocessing trick that subtracts an interpolant speeds up training, per the paper's 'value change' analysis.