3 papers
cs.AI2025
From Model Choice to Model Belief: Establishing a New Measure for LLM-Based Research
Hongshen Sun, Juanjuan Zhang
Large language models (LLMs) are increasingly used to simulate human behavior, but common practices to use LLM-generated data are inefficient. Treating an LLM's output ("model choi…
math.NA2025
Data-driven Model Reduction for Parameter-Dependent Matrix Equations via Operator Inference
Xuelian Wen, Qiuqi Li, Juan Zhang
This work develops a non-intrusive, data-driven surrogate modeling framework based on Operator Inference (OpInf) for rapidly solving parameter-dependent matrix equations in many-qu…
math.NA2024
Convergent analysis of algebraic multigrid method with data-driven parameter learning for non-selfadjoint elliptic problems
Juan Zhang, Junyue Luo
In this paper, we apply the practical GADI-HS iteration as a smoother in algebraic multigrid (AMG) method for solving second-order non-selfadjoint elliptic problem. Additionally, w…