Least-Squares Neural Network (LSNN) Method For Linear Advection-Reaction Equation: Non-constant Jumps

The least-squares ReLU neural network (LSNN) method was introduced and studied for solving linear advection-reaction equation with discontinuous solution in . The method is based on an equivalent least-squares formulation and employs ReLU neural network (NN) functions with ⌈log_2(d+1)⌉+1-layer representations for approximating solutions. In this paper, we show theoretically that the method is also capable of approximating non-constant jumps along discontinuous interfaces that are not necessarily straight lines. Numerical results for test problems with various non-constant jumps and interfaces show that the LSNN method with ⌈log_2(d+1)⌉+1 layers approximates solutions accurately with degrees of freedom less than that of mesh-based methods and without the common Gibbs phenomena along discontinuous interfaces.