ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines
This provides a scalable and efficient alternative for operator learning in scientific computing, though it is incremental as it builds on existing DeepONet and ELM frameworks.
The authors tackled the high computational cost of training Deep Operator Networks (DeepONets) by proposing ELM-DeepONets, which uses Extreme Learning Machines to eliminate backpropagation, resulting in superior accuracy and drastically reduced computational costs on benchmark problems like nonlinear ODEs and PDEs.
Deep Operator Networks (DeepONets) are among the most prominent frameworks for operator learning, grounded in the universal approximation theorem for operators. However, training DeepONets typically requires significant computational resources. To address this limitation, we propose ELM-DeepONets, an Extreme Learning Machine (ELM) framework for DeepONets that leverages the backpropagation-free nature of ELM. By reformulating DeepONet training as a least-squares problem for newly introduced parameters, the ELM-DeepONet approach significantly reduces training complexity. Validation on benchmark problems, including nonlinear ODEs and PDEs, demonstrates that the proposed method not only achieves superior accuracy but also drastically reduces computational costs. This work offers a scalable and efficient alternative for operator learning in scientific computing.