Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space

by   Kazuma Tsuji, et al.

Deep learning has achieved notable success in various fields, including image and speech recognition. One of the factors in the successful performance of deep learning is its high feature extraction ability. In this study, we focus on the adaptivity of deep learning; consequently, we treat the variable exponent Besov space, which has a different smoothness depending on the input location x. In other words, the difficulty of the estimation is not uniform within the domain. We analyze the general approximation error of the variable exponent Besov space and the approximation and estimation errors of deep learning. We note that the improvement based on adaptivity is remarkable when the region upon which the target function has less smoothness is small and the dimension is large. Moreover, the superiority to linear estimators is shown with respect to the convergence rate of the estimation error.



There are no comments yet.


page 1

page 2

page 3

page 4


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

Deep learning has exhibited superior performance for various tasks, espe...

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

Deep learning has shown high performances in various types of tasks from...

Approximation with Neural Networks in Variable Lebesgue Spaces

This paper concerns the universal approximation property with neural net...

Estimation of smooth functionals in high-dimensional models: bootstrap chains and Gaussian approximation

Let X^(n) be an observation sampled from a distribution P_θ^(n) with an ...

On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces

Deep learning has been applied to various tasks in the field of machine ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.