HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork
This addresses the problem of real-time prediction on resource-constrained hardware for applications involving complex physical dynamics, representing an incremental improvement over DeepONet.
The paper tackles the challenge of learning complex operators with limited computational resources by proposing HyperDeepONet, which uses a hypernetwork to reduce parameters and costs, achieving successful learning with fewer resources compared to benchmarks.
Fast and accurate predictions for complex physical dynamics are a significant challenge across various applications. Real-time prediction on resource-constrained hardware is even more crucial in real-world problems. The deep operator network (DeepONet) has recently been proposed as a framework for learning nonlinear mappings between function spaces. However, the DeepONet requires many parameters and has a high computational cost when learning operators, particularly those with complex (discontinuous or non-smooth) target functions. This study proposes HyperDeepONet, which uses the expressive power of the hypernetwork to enable the learning of a complex operator with a smaller set of parameters. The DeepONet and its variant models can be thought of as a method of injecting the input function information into the target function. From this perspective, these models can be viewed as a particular case of HyperDeepONet. We analyze the complexity of DeepONet and conclude that HyperDeepONet needs relatively lower complexity to obtain the desired accuracy for operator learning. HyperDeepONet successfully learned various operators with fewer computational resources compared to other benchmarks.