Cover Image

Optimal neural network approximation of smooth compositional functions on sets with low intrinsic dimension

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nagler, Thomas, Langer, Sophie
Format:	Preprint
Published:	2026
Subjects:	Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the VC dimension of deep group convolutional neural networks
by: Sepliarskaia, Anna, et al.
Published: (2024)

Statistical theory for image classification using deep convolutional neural networks with cross-entropy loss under the hierarchical max-pooling model
by: Kohler, Michael, et al.
Published: (2020)

Stein's method, smoothing and functional approximation
by: Barbour, A. D., et al.
Published: (2021)

Uniform central limit theorems for non-stationary processes via relative weak convergence
by: Palm, Nicolai, et al.
Published: (2025)

Properties of stepwise parameter estimation in high-dimensional vine copulas
by: Gauss, Jana, et al.
Published: (2025)

Asymptotics for estimating a diverging number of parameters -- with and without sparsity
by: Gauss, Jana, et al.
Published: (2024)

Fast Rates for Nonstationary Weighted Risk Minimization
by: Brock, Tobias, et al.
Published: (2026)

Asymptotics for M-type smoothing splines with non-smooth objective functions
by: Kalogridis, Ioannis
Published: (2020)

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
by: Haas, Moritz, et al.
Published: (2023)

Gaussian approximation for maximum score and non-smooth M-estimators with multiway dependence
by: Chiang, Harold D., et al.
Published: (2026)

Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables
by: Gui, Yu, et al.
Published: (2025)

Central limit theorems for vector-valued composite functionals with smoothing and applications
by: Chen, Huihui, et al.
Published: (2024)

Gaussian random field approximation via Stein's method with applications to wide random neural networks
by: Balasubramanian, Krishnakumar, et al.
Published: (2023)

Semiparametric M-estimation with overparameterized neural networks
by: Yan, Shunxing, et al.
Published: (2025)

Optimal score estimation via empirical Bayes smoothing
by: Wibisono, Andre, et al.
Published: (2024)

Strong Gaussian approximation for U-statistics in high dimensions and beyond
by: Li, Weijia, et al.
Published: (2026)

Dropout Regularization Versus $\ell_2$-Penalization in the Linear Model
by: Clara, Gabriel, et al.
Published: (2023)

Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization
by: Clara, Gabriel, et al.
Published: (2025)

The Laplace approximation accuracy in high dimensions: a refined analysis and new skew adjustment
by: Katsevich, Anya
Published: (2023)

Statistical learnability of smooth boundaries via pairwise binary classification with deep ReLU networks
by: Waida, Hiroki, et al.
Published: (2025)

Simultaneous inference for monotone and smoothly time-varying functions under complex temporal dynamics
by: Luo, Tianpai, et al.
Published: (2023)

On the probability of linear separability through intrinsic volumes
by: Kuchelmeister, Felix
Published: (2024)

Scale-adaptive and robust intrinsic dimension estimation via optimal neighbourhood identification
by: Di Noia, Antonio, et al.
Published: (2024)

Inference on the attractor spaces via functional approximation
by: Franchi, Massimo, et al.
Published: (2025)

Optimal estimation of a factorizable density using diffusion models with ReLU neural networks
by: Fan, Jianqing, et al.
Published: (2025)

Improved dimension dependence in the Bernstein von Mises Theorem via a new Laplace approximation bound
by: Katsevich, Anya
Published: (2023)

On standardness and the non-estimability of certain functionals of a set
by: Cholaquidis, Alejandro, et al.
Published: (2023)

Gaussian mixture layers for neural networks
by: Chewi, Sinho, et al.
Published: (2025)

Stochastic approximation in infinite dimensions
by: Karandikar, Rajeeva Laxman, et al.
Published: (2024)

Minimax estimation of Functional Principal Components from noisy discretized functional data: the case of smooth processes
by: Bourarach, Nassim, et al.
Published: (2026)

Generalized van Trees inequality: Local minimax bounds for non-smooth functionals and irregular statistical models
by: Takatsu, Kenta, et al.
Published: (2024)

Time-Inhomogeneous Preconditioned Langevin Dynamics
by: Falk, Alexander, et al.
Published: (2026)

Gaussian and bootstrap approximations for functional principal component regression
by: Yeon, Hyemin
Published: (2026)

Hoeffding-type decomposition for $U$-statistics on bipartite networks
by: Minh, Tâm Le, et al.
Published: (2023)

Polynomial approximation of noisy functions
by: Matsuda, Takeru, et al.
Published: (2024)

On the rates of convergence for learning with convolutional neural networks
by: Yang, Yunfei, et al.
Published: (2024)

Anisotropic local constant smoothing for change-point regression function estimation
by: Thompson, John R. J., et al.
Published: (2020)

Gaussian universality for approximately polynomial functions of high-dimensional data
by: Huang, Kevin Han, et al.
Published: (2024)

Regularisation for the approximation of functions by mollified discretisation methods
by: Pouchol, Camille, et al.
Published: (2024)

Provable local learning rule by expert aggregation for a Hawkes network
by: Jaffard, Sophie, et al.
Published: (2023)