Copertina

Optimal lower Lipschitz bounds for ReLU layers, saturation, and phase retrieval

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Freeman, Daniel, Haider, Daniel
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Numerical Analysis Functional Analysis
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Two-hidden-layer ReLU neural networks and finite elements
di: Jin, Pengzhan
Pubblicazione: (2024)

ReLU neural network approximation to piecewise constant functions
di: Cai, Zhiqiang, et al.
Pubblicazione: (2024)

Weighted variation spaces and approximation by shallow ReLU networks
di: DeVore, Ronald, et al.
Pubblicazione: (2023)

Sharp Lower Bounds for Linearized ReLU^k Approximation on the Sphere
di: Mao, Tong, et al.
Pubblicazione: (2025)

Higher Order Approximation Rates for ReLU CNNs in Korobov Spaces
di: Li, Yuwen, et al.
Pubblicazione: (2025)

Sobolev Approximation of Deep ReLU Networks in Log-Barron Space
di: Song, Changhoon, et al.
Pubblicazione: (2026)

Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity
di: Hong, Ruiyang, et al.
Pubblicazione: (2024)

Memorization capacity of deep ReLU neural networks characterized by width and depth
di: Yang, Xin, et al.
Pubblicazione: (2026)

On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks
di: Yang, Yunfei
Pubblicazione: (2024)

Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks
di: Yang, Yunfei, et al.
Pubblicazione: (2026)

The Cahill-Casazza-Daubechies problem on Hölder stable phase retrieval
di: Freeman, Daniel, et al.
Pubblicazione: (2025)

How Analysis Can Teach Us the Optimal Way to Design Neural Operators
di: Le, Vu-Anh, et al.
Pubblicazione: (2024)

Multilevel Picard approximations and deep neural networks with ReLU, leaky ReLU, and softplus activation overcome the curse of dimensionality when approximating semilinear parabolic partial differential equations in $L^p$-sense
di: Neufeld, Ariel, et al.
Pubblicazione: (2024)

Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation
di: He, Juncai, et al.
Pubblicazione: (2023)

Some lower bounds for optimal sampling recovery of functions with mixed smoothness
di: Gasnikov, A., et al.
Pubblicazione: (2024)

Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis
di: Katende, Ronald
Pubblicazione: (2025)

Quantum Harmonic Analysis and the Structure in Data: Augmentation
di: Doerfler, Monika, et al.
Pubblicazione: (2025)

Don't Fix the Basis -- Learn It: Spectral Representation with Adaptive Basis Learning for PDEs
di: Zhao, Xuxiang, et al.
Pubblicazione: (2026)

PINNs error estimates for nonlinear equations in $\mathbb{R}$-smooth Banach spaces
di: Gao, Jiexing, et al.
Pubblicazione: (2023)

Construction of generalized samplets in Banach spaces
di: Balazs, Peter, et al.
Pubblicazione: (2024)

On the growth of the parameters of approximating ReLU neural networks
di: Morina, Erion, et al.
Pubblicazione: (2024)

On the algorithmic construction of deep ReLU networks
di: Huybrechs, Daan
Pubblicazione: (2025)

Approximation Rates and VC-Dimension Bounds for (P)ReLU MLP Mixture of Experts
di: Kratsios, Anastasis, et al.
Pubblicazione: (2024)

Nearly Optimal Approximation Rates for Deep Super ReLU Networks on Sobolev Spaces
di: Yang, Yahong, et al.
Pubblicazione: (2023)

Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces
di: Siegel, Jonathan W.
Pubblicazione: (2022)

Exponential Expressivity of ReLU$^k$ Neural Networks on Gevrey Classes with Point Singularities
di: Opschoor, Joost A. A., et al.
Pubblicazione: (2024)

A Structure-Guided Gauss-Newton Method for Shallow ReLU Neural Network
di: Cai, Zhiqiang, et al.
Pubblicazione: (2024)

A Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learning
di: Yang, Jia-Qi, et al.
Pubblicazione: (2025)

Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
di: Berner, Julius, et al.
Pubblicazione: (2025)

Which Spaces can be Embedded in $L_p$-type Reproducing Kernel Banach Space? A Characterization via Metric Entropy
di: Lu, Yiping, et al.
Pubblicazione: (2024)

Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks
di: Liang, Luxu, et al.
Pubblicazione: (2024)

Deep ReLU Neural Network Emulation in High-Frequency Acoustic Scattering
di: Henríquez, Fernando, et al.
Pubblicazione: (2024)

Integral Representations of Sobolev Spaces via ReLU$^k$ Activation Function and Optimal Error Estimates for Linearized Networks
di: Liu, Xinliang, et al.
Pubblicazione: (2025)

Schauder Bases for $C[0, 1]$ Using ReLU, Softplus and Two Sigmoidal Functions
di: Ganesh, Anand, et al.
Pubblicazione: (2025)

Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections
di: Kratsios, Anastasis, et al.
Pubblicazione: (2025)

On the approximation of vector-valued functions by volume sampling
di: Kressner, Daniel, et al.
Pubblicazione: (2023)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense
di: Ackermann, Julia, et al.
Pubblicazione: (2023)

Aliasing in Convnets: A Frame-Theoretic Perspective
di: Haider, Daniel, et al.
Pubblicazione: (2025)

Nonlocal techniques for the analysis of deep ReLU neural network approximations
di: Schneider, Cornelia, et al.
Pubblicazione: (2025)

On the existence of optimal shallow feedforward networks with ReLU activation
di: Dereich, Steffen, et al.
Pubblicazione: (2023)