On the approximation of rough functions with deep neural networks

2019/12/13 by De Ryck, Tim, Mishra, Siddhartha, Ray, Deep · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Numerical Analysis (math.NA)

paper · doi:10.48550/arxiv.1912.06732

Abstract

Deep neural networks and the ENO procedure are both efficient frameworks for approximating rough functions. We prove that at any order, the ENO interpolation procedure can be cast as a deep ReLU neural network. This surprising fact enables the transfer of several desirable properties of the ENO procedure to deep neural networks, including its high-order accuracy at approximating Lipschitz functions. Numerical tests for the resulting neural networks show excellent performance for approximating solutions of nonlinear conservation laws and at data compression.

Cited by

• PINN-DG: Residual neural network methods trained with Finite Elements

Related

• Nonlinear Approximation and (Deep) ReLU Networks
• Approximation Power of Deep Neural Networks: an explanatory mathematical survey
• Neural Network Approximation of Refinable Functions
• Deep Neural Networks Learn Non-Smooth Functions Effectively
• Simultaneous Neural Network Approximation for Smooth Functions