Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations
cs.LG, stat.ML
Submitted: 2026-08-31
Updated: 2026-08-31
Terminology
Sources
- Deep learning and the rate of approximation by flows
- Kilobyte Models: Neural Networks as a Seed and a Quantized Latent
- On the Activation Function Dependence of the Spectral Bias of Neural Networks
- Deep Neural Network Approximation of Invariant Functions through Dynamical Systems
- On the Universal Approximation Property of Deep Fully Convolutional Neural Networks
- Do Neural Networks Really Beat the Curse of Dimensionality? A Bit-Complexity View
- Layer-wise Geometric Approximation Rates for Deep Networks
- Multigrade Neural Network 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks