paper-with-me

Papers

Target Parameterization in Diffusion Models for Nonlinear Spatiotemporal System Identification

2026-04-19 · Achraf El Messaoudi, Noureddine Khaous, Karim Cherifi arxiv

Machine learning is becoming increasingly important for nonlinear system identification, including dynamical systems with spatially distributed outputs. However, classical identification and forecasting approaches become markedly less reliable in turbulent-flow regimes, where the dynamics are high-dimensional, strongly nonlinear, and highly sensitive to compounding rollout errors. Diffusion-based models have recently shown improved robustness in this setting and offer probabilistic inference capabilities, but many current implementations inherit target parameterizations from image generation, most commonly noise or velocity prediction. In this work, we revisit this design choice in the context of nonlinear spatiotemporal system identification. We consider a simple, self-contained patch-based transformer that operates directly on physical fields and use turbulent flow simulation as a representative testbed. Our results show that clean-state prediction consistently improves rollout stability and reduces long-horizon error relative to velocity- and noise-based objectives, with the advantage becoming more pronounced as the per-token dimensionality increases. These findings identify target parameterization as a key modeling choice in diffusion-based identification of nonlinear systems with spatial outputs in turbulent regimes.

📄 PDF Abstract BibTeX arXiv:2604.17566

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Variational multiscale reinforcement learning for discovering reduced order closure models of nonlinear spatiotemporal transport systems

2022-07-07 · Omer San, Suraj Pawar, Adil Rasheed

A central challenge in the computational modeling and simulation of a multitude of science applications is to achieve robust and accurate closures for their coarse-grained representations due to underlying highly nonline…

Reinforcement Learning (RL)

Linear Stability Hypothesis and Rank Stratification for Nonlinear Models

2022-11-21 · Yaoyu Zhang, Zhongwang Zhang, Leyang Zhang, Zhiwei Bai 외

Models with nonlinear architectures/parameterizations such as deep neural networks (DNNs) are well known for their mysteriously good generalization performance at overparameterization. In this work, we tackle this myster…

A Causality-Based Learning Approach for Discovering the Underlying Dynamics of Complex Systems from Partial Observations with Stochastic Parameterization

2022-08-19 · Nan Chen, Yinling Zhang

Discovering the underlying dynamics of complex systems from data is an important practical topic. Constrained optimization algorithms are widely utilized and lead to many successes. Yet, such purely data-driven methods m…

Causal Inferenceparameter estimation

KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra

2026-02-15 · Liangyu Su, Jun Shu, Rui Liu, Deyu Meng 외 arxiv

Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although data-driven models can achieve accurate shor…

Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approaches

2025-04-07 · Eloi Moliner, Michal Švento, Alec Wright, Lauri Juvela 외

Accurately estimating nonlinear audio effects without access to paired input-output signals remains a challenging problem.This work studies unsupervised probabilistic approaches for solving this task. We introduce a meth…