Pith. sign in

REVIEW 4 cited by

The Barron Space and the Flow-induced Function Spaces for Neural Network Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1906.08039 v2 pith:2NEW4YQU submitted 2019-06-18 cs.LG math.PRstat.ML

Weinan E , Chao Ma , Lei Wu This is my paper · ORCID
classification cs.LGmath.PRstat.ML
keywords spacemodelsneuralnetworkapproximationbarronfunctiondirect
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

One of the key issues in the analysis of machine learning models is to identify the appropriate function space and norm for the model. This is the set of functions endowed with a quantity which can control the approximation and estimation errors by a particular machine learning model. In this paper, we address this issue for two representative neural network models: the two-layer networks and the residual neural networks. We define the Barron space and show that it is the right space for two-layer neural network models in the sense that optimal direct and inverse approximation theorems hold for functions in the Barron space. For residual neural network models, we construct the so-called flow-induced function space, and prove direct and inverse approximation theorems for this space. In addition, we show that the Rademacher complexity for bounded sets under these norms has the optimal upper bounds.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A deformation-based framework for learning solution mappings of PDEs defined on varying domains

    math.NA 2024-12 conditional novelty 7.0 of 10

    A deformation-based metric framework lets neural operators learn PDE solution maps on non-diffeomorphic, varying domains, with a convergence proof for Poisson on star domains and a D2E variant that avoids deformation-...

  2. Shallow neural network yields regularization for ill-posed inverse problems

    math.NA 2025-11 conditional novelty 6.0 of 10

    The number of neurons in a shallow ReLU network can serve as a regularization parameter for ill-posed inverse problems, with theoretically derived scaling n(δ)=O(δ^{-2/θ}).

  3. ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals

    cs.LG 2025-01 conditional novelty 6.0 of 10

    ResKoopNet learns Koopman eigenpairs by minimizing the spectral residual over neural-network dictionaries, reporting fuller spectra and better latent-state separation than existing Koopman methods.

  4. Momentum-Accelerated Richardson(m) and Their Multilevel Neural Solvers

    math.NA 2024-12 conditional novelty 4.0 of 10

    Neural networks predict the weights of momentum-accelerated long-step Richardson iterations, reducing iteration counts on anisotropic diffusion and Helmholtz problems versus Chebyshev-based iterations in numerical exp...

Pith tools