Neural Network Approximation Theory

Overview

The field asks which functions and operators neural networks can represent, how many parameters or layers they need, and how approximation error depends on target smoothness and structure. Researchers prove constructive approximation rates and lower bounds for architectures including ReLU and smooth-activation networks, Kolmogorov-Arnold networks, Transformers, and neural operators, often using tools from harmonic analysis, approximation spaces, and geometry. Applications include nonparametric regression and PDE solution maps, where Sobolev, Barron, Besov, compositional, and symmetry-aware assumptions can yield sharper rates than general worst-case guarantees. A central tension is that favorable rates often rely on strong structure or idealized parameter precision, while optimization, sampling, and finite-precision limits can determine whether those guarantees are useful in practice.

Latest papers

CardsList

264 papers22 papers in the last four weeks, down 27% on the four weeks before. 0.2% of all new papers.

  1. Structure-Preserving Neural Approximation of Convex, Semiconvex, and Quasiconvex Functions

    Nov 18, 2026Yeachan Park, Yeoneung KimStructure-Preserving Neural NetworksNeural Network Approximation Theory

  2. Optimal Deep Nonparametric Regression with Uniformly Bounded Lipschitz Constants

    Nov 18, 2026Jiaxin Shi, Ziyuan Chen, Jian Huang +1Nonparametric RegressionNeural Network Approximation Theory

  3. Learning from Duality in Neural Network Field Theories

    Nov 16, 2026Pietro Capuozzo, Brandon Robinson, Benjamin SuzzoniFinite-Width Neural Network TheoryNeural Network Approximation Theory

  4. Error Analysis of Deep Learning

    Nov 15, 2026Yuling Jiao, Peiying Wu, Jerry Zhijian Yang +1Statistical Learning TheoryDeep Learning Optimization

  5. Barron Approximation and locally optimal weight densities for shallow neural networks

    Nov 15, 2026G. WelperShallow Neural NetworksNeural Network Optimization

  6. Universal Approximation Theorem for Metaplectic Neural Operators

    Nov 10, 2026Ahmed Abdeljawad, Malek Yacine RezougUniversal ApproximationNeural Operators

  7. Geometry-Dependent Approximation and Stability Properties of Shallow ReLUk^k Networks on Bounded Euclidean Domains

    Nov 10, 2026Yuqing Liu, Tong Mao, Jinchao XuShallow Neural NetworksReLU Neural Networks

  8. Operator Learning of Microstructure-Dependent Internal-Variable Models for Inelastic Homogenization: Approximation and Complexity

    Nov 9, 2026Lianghao Cao, George Stepaniants, Andrew M. StuartOperator LearningNeural Operators

  9. Projected Neural Additive Models as Universal Approximators

    Nov 6, 2026Nhon N. Phan, Qiang Du, John D. Clayton +1Function ApproximationNeural Network Approximation Theory

  10. Point interpolation and distributional universality in flow-based generative models

    Nov 3, 2026Antonio Álvarez-López, Jingpu Cheng, Liyan Zhang +1Flow-Based Generative ModelingGenerative Modeling

  11. Observable-Specific Validity Tests for Scientific AI: Controlled Approximations and Intervention Response

    Oct 30, 2026Xiaoshn Nee, Haobo Zhong, Xiaomin NiScientific MLNeural Network Approximation Theory

  12. Meshless Latent Dynamics Models for Model Order Reduction of time-dependent Partial Differential Equations

    Oct 29, 2026Lorenzo Tomada, Federico Pichi, Gianluigi RozzaLatent Dynamics ModelingReduced-Order Modeling

  13. Representation Complexity Along Learning Trajectories: Trading Width for Precision and Time

    Oct 28, 2026Ryan Singh, Miguel De Llanza, Christopher L. BuckleyOverparameterized Neural NetworkNeural Network Training Dynamics

  14. Boundary Geometry Determines Optimal Shallow ReLU Approximation under Weighted Coefficient Constraints

    Oct 27, 2026Jia-Qi Yang, Lei ShiNeural Network Approximation TheoryShallow Neural Networks

  15. Universal neural network approximation of symmetric polyconvex energies and envelopes

    Oct 23, 2026Florian GammerNeural Network Approximation TheoryInput Convex Neural Networks

  16. Tractable Inference with Kolmogorov-Arnold Networks

    Oct 21, 2026Juan Diego Toscano, Sascha Ranftl, Zhiwei Gao +2Kolmogorov-Arnold NetworksNeural Surrogate Modeling

  17. Constructive Universal Approximation by Infinite-Dimensional Neural Networks via Gaussian-Weighted Ridgelet Transform

    Oct 16, 2026Sho Sonoda, Luca Galimberti, Yuanchao Xu +2Neural Network Approximation TheoryNeural Operators

  18. Wavelength Diversity Expands the Expressive Power of Optical Computing

    Oct 16, 2026Shiqi Chen, Che-Yung Shen, Parnian Ghapandar Kashani +2Photonic ComputingUniversal Approximation

  19. Optimal approximation of smooth functions by ReLU neural networks

    Oct 15, 2026Thomas NaglerNeural Network Approximation TheoryReLU Neural Networks

  20. Activation-Adjacent Layer Normalization: Effects on Approximation Power

    Oct 15, 2026Yunhao Ni, Yuxin Guo, Jie Luo +2Layer NormalizationNeural Network Approximation Theory