paper-with-me

Papers

Approximation capabilities of neural networks on unbounded domains

2019-10-21 · Ming-Xi Wang, Yang Qu

In this paper, we prove that a shallow neural network with a monotone sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function can arbitrarily well approximate any L^p(p>=2) integrable functions defined on R*[0,1]^n. We also prove that a shallow neural network with a sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function expresses no nonzero integrable function defined on the Euclidean plane. Together with a recent result that the deep ReLU network can arbitrarily well approximate any integrable function on Euclidean spaces, we provide a new perspective on the advantage of multiple hidden layers in the context of ReLU networks. Lastly, we prove that the ReLU network with depth 3 is a universal approximator in L^p(R^n).

📄 PDF Abstract BibTeX arXiv:1910.09293

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ELU 설명 없음
(TravEL!!Guide)How Do I File a Claim with Expedia? How Do I File a Claim with Expedia? Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Fast Help & Exclusive Travel Discounts!Need to file a claim with…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Weighted Sobolev Approximation Rates for Neural Networks on Unbounded Domains

2024-11-06 · Ahmed Abdeljawad, Thomas Dittrich

In this work, we consider the approximation capabilities of shallow neural networks in weighted Sobolev spaces for functions in the spectral Barron space. The existing literature already covers several cases, in which th…

Domain-Decomposed Randomized Neural Networks for Partial Differential Equations in Unbounded Domains

2026-06-30 · Haixin Wang, Haoning Dang, Fei Wang, Shimin Guo arxiv

Partial differential equations on unbounded domains are challenging because the exterior region must be represented without excessive truncation error. Truncation-based methods often require problem-dependent artificial …

Universal approximation results for neural networks with non-polynomial activation function over non-compact domains

2024-10-18 · Ariel Neufeld, Philipp Schmocker

This paper extends the universal approximation property of single-hidden-layer feedforward neural networks beyond compact domains, which is of particular interest for the approximation within weighted $C^k$-spaces and we…

Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes

2025-12-17 · Hanqing Jin, Renyuan Xu, Yanzhao Yang arxiv

We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics…

Reinforcement Learning

Weighted variation spaces and approximation by shallow ReLU networks

2023-07-28 · Ronald DeVore, Robert D. Nowak, Rahul Parhi, Jonathan W. Siegel

We investigate the approximation of functions $f$ on a bounded domain $\Omega\subset \mathbb{R}^d$ by the outputs of single-hidden-layer ReLU neural networks of width $n$. This form of nonlinear $n$-term dictionary appro…