Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study
Provides a theoretical foundation for neural scaling laws in operator learning, which is important for understanding and predicting performance in scientific computing and engineering applications.
The paper develops a theoretical framework to quantify neural scaling laws for deep operator networks (e.g., DeepONet) and deep ReLU networks, establishing relationships between approximation/generalization errors and model/data size, including tighter bounds for low-dimensional input structures.
Neural scaling laws play a pivotal role in the performance of deep neural networks and have been observed in a wide range of tasks. However, a complete theoretical framework for understanding these scaling laws remains underdeveloped. In this paper, we explore the neural scaling laws for deep operator networks, which involve learning mappings between function spaces, with a focus on the Chen and Chen style architecture. These approaches, which include the popular Deep Operator Network (DeepONet), approximate the output functions using a linear combination of learnable basis functions and coefficients that depend on the input functions. We establish a theoretical framework to quantify the neural scaling laws by analyzing its approximation and generalization errors. We articulate the relationship between the approximation and generalization errors of deep operator networks and key factors such as network model size and training data size. Moreover, we address cases where input functions exhibit low-dimensional structures, allowing us to derive tighter error bounds. These results also hold for deep ReLU networks and other similar structures. Our results offer a partial explanation of the neural scaling laws in operator learning and provide a theoretical foundation for their applications.