Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Progressive Approximation in Deep Residual Networks: Theory and Validation
Wei Wang, Xiao-Yong Wei, Qing Li
The Universal Approximation Theorem (UAT) guarantees universal function approximation but does not explain how residual models distribute approximation across layers. We reframe re…
cs.LG2025
A General Method for Proving Networks Universal Approximation Property
Wei Wang
Deep learning architectures are highly diverse. To prove their universal approximation properties, existing works typically rely on model-specific proofs. Generally, they construct…