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

09/23/2020
by   Kazuma Tsuji, et al.
18

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/28/2019

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

Deep learning has exhibited superior performance for various tasks, espe...
research
10/18/2018

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...
research
07/08/2020

Approximation with Neural Networks in Variable Lebesgue Spaces

This paper concerns the universal approximation property with neural net...
research
05/30/2023

Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input

Despite the great success of Transformer networks in various application...
research
12/10/2021

Modular-proximal gradient algorithms in variable exponent Lebesgue spaces

We consider structured optimisation problems defined in terms of the sum...

Please sign up or login with your details

Forgot password? Click here to reset