Efficient Approximation to Analytic and $L^p$ functions by Height-Augmented ReLU Networks
This work addresses fundamental limitations in neural network approximation theory, offering a theoretically grounded pathway for designing more parameter-efficient networks, which is incremental but with notable theoretical advances.
The paper tackles the problem of approximating analytic and L^p functions with neural networks by introducing a three-dimensional architecture that improves representation efficiency, achieving substantially improved exponential approximation rates for analytic functions and providing the first quantitative, non-asymptotic high-order approximation for general L^p functions.
This work addresses two fundamental limitations in neural network approximation theory. We demonstrate that a three-dimensional network architecture enables a significantly more efficient representation of sawtooth functions, which serves as the cornerstone in the approximation of analytic and $L^p$ functions. First, we establish substantially improved exponential approximation rates for several important classes of analytic functions and offer a parameter-efficient network design. Second, for the first time, we derive a quantitative and non-asymptotic approximation of high orders for general $L^p$ functions. Our techniques advance the theoretical understanding of the neural network approximation in fundamental function spaces and offer a theoretically grounded pathway for designing more parameter-efficient networks.