Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Yuxin, Hu, Yuanzhe, Zhong, Xiaokun, Wang, Xiaopeng, Lu, Haiquan, Pang, Tianyu, Mahoney, Michael W., Yan, Yujun, Ren, Pu, Yang, Yaoqing
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917542534053888
author Wang, Yuxin
Hu, Yuanzhe
Zhong, Xiaokun
Wang, Xiaopeng
Lu, Haiquan
Pang, Tianyu
Mahoney, Michael W.
Yan, Yujun
Ren, Pu
Yang, Yaoqing
author_facet Wang, Yuxin
Hu, Yuanzhe
Zhong, Xiaokun
Wang, Xiaopeng
Lu, Haiquan
Pang, Tianyu
Mahoney, Michael W.
Yan, Yujun
Ren, Pu
Yang, Yaoqing
contents Neural networks trained under different hyperparameter settings can fall into distinct training "regimes," with consistent behavior within regimes and qualitative differences across regimes. In this paper, we study such multi-regime behavior in scientific machine learning (SciML) models through a regime-aware diagnostic framework that jointly analyzes performance, training dynamics, and loss-landscape geometry. We identify three key findings: (i) a consistent three-regime structure emerges across many standard SciML models, different constraint enforcements, and various optimizer designs; (ii) optimization effectiveness is regime-specific, with no single method performing well across all regimes; and (iii) SciML models can exhibit fine-grained failure modes that can challenge conventional interpretations of standard loss-landscape metrics. Our results provide an approach to establish a unified, task-oblivious perspective on failure modes in SciML and to inform regime-aware guidance for improving robustness. We validate these findings across widely-used SciML models, including physics-informed neural networks, neural operators, and neural ordinary differential equations, on benchmarks spanning representative ordinary and partial differential equations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29153
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
Wang, Yuxin
Hu, Yuanzhe
Zhong, Xiaokun
Wang, Xiaopeng
Lu, Haiquan
Pang, Tianyu
Mahoney, Michael W.
Yan, Yujun
Ren, Pu
Yang, Yaoqing
Machine Learning
Artificial Intelligence
Computational Physics
Neural networks trained under different hyperparameter settings can fall into distinct training "regimes," with consistent behavior within regimes and qualitative differences across regimes. In this paper, we study such multi-regime behavior in scientific machine learning (SciML) models through a regime-aware diagnostic framework that jointly analyzes performance, training dynamics, and loss-landscape geometry. We identify three key findings: (i) a consistent three-regime structure emerges across many standard SciML models, different constraint enforcements, and various optimizer designs; (ii) optimization effectiveness is regime-specific, with no single method performing well across all regimes; and (iii) SciML models can exhibit fine-grained failure modes that can challenge conventional interpretations of standard loss-landscape metrics. Our results provide an approach to establish a unified, task-oblivious perspective on failure modes in SciML and to inform regime-aware guidance for improving robustness. We validate these findings across widely-used SciML models, including physics-informed neural networks, neural operators, and neural ordinary differential equations, on benchmarks spanning representative ordinary and partial differential equations.
title Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
topic Machine Learning
Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2605.29153