An Efficient Learning Method to Connect Observables
This work addresses the need for efficient surrogate models in topics requiring robust predictions, but it appears incremental as it builds on existing emulators like Eigenvector Continuation and Parametric Matrix Model.
The paper tackles the problem of constructing fast and accurate surrogate models for robust predictions by introducing the Multiparameter Eigenvalue Problem (MEP) emulator, which connects emulators to make predictions directly from observables to observables, and demonstrates its performance on a one-dimensional lattice simulation and with $^{28}$O as an example.
Constructing fast and accurate surrogate models is a key ingredient for making robust predictions in many topics. We introduce a new model, the Multiparameter Eigenvalue Problem (MEP) emulator. The new method connects emulators and can make predictions directly from observables to observables. We present that the MEP emulator can be trained with data from Eigenvector Continuation (EC) and Parametric Matrix Model (PMM) emulators. A simple simulation on a one-dimensional lattice confirms the performance of the MEP emulator. Using $^{28}$O as an example, we also demonstrate that the predictive probability distribution of the target observables can be easily obtained through the new emulator.