A Closed-Form Formula for Consistent Lipschitz Regression on Metric Spaces with Sparse Neural Network Realizations
stat.ML, cs.LG
Submitted: 2026-09-02
Updated: 2026-09-02
Comments: 75 pages, 17 figures
Code: https://github.com/hradghoukasian/closed-form-nn
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Do we really need the Rademacher complexities?
- New universal operator approximation theorem for encoder-decoder architectures
- Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity
- Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data
- Is In-Context Universality Enough? MLPs are Also Universal In-Context
- Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections
- An Approximation Theory for Metric Space-Valued Functions With A View Towards Deep Learning
- Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning
- A note on dichotomies for metric transforms
- Universal approximation property of Banach space-valued random feature models including random neural networks
- Generating Rectifiable Measures through Neural Networks
- Embedding Dimension Lower Bounds for Universality of Deep Sets and Janossy Pooling
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey