paper-with-me

홈 › Papers

Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space

2019-10-28 · NeurIPS 2021 12 · Taiji Suzuki, Atsushi Nitanda

Deep learning has exhibited superior performance for various tasks, especially for high-dimensional datasets, such as images. To understand this property, we investigate the approximation and estimation ability of deep learning on anisotropic Besov spaces. The anisotropic Besov space is characterized by direction-dependent smoothness and includes several function classes that have been investigated thus far. We demonstrate that the approximation error and estimation error of deep learning only depend on the average value of the smoothness parameters in all directions. Consequently, the curse of dimensionality can be avoided if the smoothness of the target function is highly anisotropic. Unlike existing studies, our analysis does not require a low-dimensional structure of the input data. We also investigate the minimax optimality of deep learning and compare its performance with that of the kernel method (more generally, linear estimators). The results show that deep learning has better dependence on the input dimensionality if the target function possesses anisotropic smoothness, and it achieves an adaptive rate for functions with spatially inhomogeneous smoothness.

📄 PDF Abstract BibTeX arXiv:1910.12799

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces

2026-05-12 · Jeunghun Oh, Kyeongwon Lee, Jaeyong Lee, Lizhen Lin arxiv

We study posterior contraction rates for sparse Bayesian Kolmogorov-Arnold networks (KANs) over anisotropic Besov spaces, providing a statistical foundation of KANs from a Bayesian point of view. We show that sparse Baye…

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

2026-05-29 · Yunfei Yang, Jun Fan arxiv

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 $L$, r…

Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality

2018-10-18 · ICLR 2019 5 · Taiji Suzuki

Deep learning has shown high performances in various types of tasks from visual recognition to natural language processing, which indicates superior flexibility and adaptivity of deep learning. To understand this phenome…

Deep Learning

Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness

2021-09-29 · ICLR 2022 4 · Sho Okumoto, Taiji Suzuki

Among a wide range of success of deep learning, convolutional neural networks have been extensively utilized in several tasks such as speech recognition, image processing, and natural language processing, which require i…

speech-recognitionSpeech Recognition

Optimal Learning with Anisotropic Gaussian SVMs

2018-10-04 · Hanyuan Hang, Ingo Steinwart

This paper investigates the nonparametric regression problem using SVMs with anisotropic Gaussian RBF kernels. Under the assumption that the target functions are resided in certain anisotropic Besov spaces, we establish …

regression