Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One
Qi Zhou, Xuan Zhou, Xiao-Song Yang
cs.LG, stat.ML
Submitted: 2026-07-06
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Approximating Continuous Functions by ReLU Nets of Minimal Width
- Deep, Skinny Neural Networks are not Universal Approximators
- Adam: A Method for Stochastic Optimization
- Mathematical theory of deep learning
- Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theory
- Minimum Width of Deep Narrow Networks for Universal Approximation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks