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

• URL: http://arxiv.org/abs/2605.29153v1
• Date: Wed, 27 May 2026 22:33:03 GMT
• Title: Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
• Abstract summary: We study such multi-regime behavior in scientific machine learning (SciML) models through a regime-aware diagnostic framework.<n>We identify three key findings: (i) a consistent three-regime structure emerges across many standard SciML models, different constraint enforcements, and various 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.
• Score: 72.59989168322774
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hierarchical Inference and Closure Learning via Adaptive Surrogates for ODEs and PDEs [15.38864225184245]
  Inverse problems are the task of calibrating models to match data.<n>We develop a principled methodology for leveraging data from collections of distinct yet related physical systems.<n>We learn the shared unknown dynamics in the form of an ML-based closure model.
  arXiv  Detail & Related papers  (2026-03-04T10:30:08Z)
• ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations [54.886931928255564]
  Low-rank adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning method in deep transfer learning.<n>We propose a novel continuous-time optimization dynamic for LoRA factor matrices in the form of an ordinary differential equation (ODE)<n>We show that ODELoRA achieves stable feature learning, a property that is crucial for training deep neural networks at different scales of problem dimensionality.
  arXiv  Detail & Related papers  (2026-02-07T10:19:36Z)
• Introduction to optimization methods for training SciML models [4.970277730082773]
  Optimization is central to both modern machine learning (ML) and scientific machine learning (SciML)<n>This document provides a unified introduction to optimization methods in ML and SciML, emphasizing how problem structure shapes algorithmic choices.
  arXiv  Detail & Related papers  (2026-01-15T09:36:15Z)
• FMint-SDE: A Multimodal Foundation Model for Accelerating Numerical Simulation of SDEs via Error Correction [7.463977095236658]
  We introduce a novel multi-modal foundation model for large-scale simulations of differential equations: FMint-SDE.<n>Based on a decoder-only transformer with in-context learning, FMint-SDE learns a universal error-correction scheme.<n>We evaluate our models on a suite of challenging SDE benchmarks spanning applications in molecular dynamics, mechanical systems, finance, and biology.
  arXiv  Detail & Related papers  (2025-10-31T04:49:41Z)
• Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning [58.533203990515034]
  Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL)<n>We show that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements.<n>We finally distill these insights into Module-Specific Training (MST), a practical framework that exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.
  arXiv  Detail & Related papers  (2025-10-14T03:03:08Z)
• On Linear Mode Connectivity of Mixture-of-Experts Architectures [1.6747713135100666]
  We investigate the phenomenon of linear Mode Connectivity (LMC) in neural networks.<n>LMC is a notable phenomenon in the loss landscapes of neural networks, wherein independently trained models have been to be connected--up to varying symmetries of an algorithm.
  arXiv  Detail & Related papers  (2025-09-14T16:51:41Z)
• Recursive Learning of Asymptotic Variational Objectives [49.69399307452126]
  General state-space models (SSMs) are widely used in statistical machine learning and are among the most classical generative models for sequential time-series data. Online sequential IWAE (OSIWAE) allows for online learning of both model parameters and a Markovian recognition model for inferring latent states. This approach is more theoretically well-founded than recently proposed online variational SMC methods.
  arXiv  Detail & Related papers  (2024-11-04T16:12:37Z)
• A Competitive Learning Approach for Specialized Models: A Solution for Complex Physical Systems with Distinct Functional Regimes [0.0]
  We propose a novel competitive learning approach for obtaining data-driven models of physical systems. The primary idea behind the proposed approach is to employ dynamic loss functions for a set of models that are trained concurrently on the data.
  arXiv  Detail & Related papers  (2023-07-19T23:29:40Z)
• Equivariant vector field network for many-body system modeling [65.22203086172019]
  Equivariant Vector Field Network (EVFN) is built on a novel equivariant basis and the associated scalarization and vectorization layers. We evaluate our method on predicting trajectories of simulated Newton mechanics systems with both full and partially observed data.
  arXiv  Detail & Related papers  (2021-10-26T14:26:25Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.