Deep ReLU networks efficiently learn smooth functions

By PulseAugur Editorial · [2 sources] · 2026-05-29 11:04

Researchers have published a paper detailing how deep ReLU neural networks can efficiently approximate and learn smooth functions. The study extends previous findings to anisotropic and mixed smooth function classes, establishing new approximation rates. These results demonstrate that deep ReLU networks can achieve near-optimal learning rates for various smooth function types. AI

IMPACT Establishes theoretical bounds for deep learning approximation, potentially guiding future model architecture and training.

RANK_REASON The cluster contains an academic paper published on arXiv.

Read on arXiv stat.ML →

paper
other

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

arXiv stat.ML TIER_1 English(EN) · Yunfei Yang, Jun Fan · 2026-06-01 04:00

Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks

arXiv:2605.31152v1 Announce Type: new Abstract: This paper studies how efficiently deep ReLU neural networks can approximate and learn smooth functions. When the error is measured in $L^p([0,1]^d)$ norm and the approximator is a network with width $W$ and depth $L$, recent works …
arXiv stat.ML TIER_1 English(EN) · Jun Fan · 2026-05-29 11:04

Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks

This paper studies how efficiently deep ReLU neural networks can approximate and learn smooth functions. When the error is measured in $L^p([0,1]^d)$ norm and the approximator is a network with width $W$ and depth $L$, recent works have proven the supper approximation rate $\math…

COVERAGE [2]

Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks

Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks

RELATED ENTITIES

RELATED TOPICS