mlsanityData to 14 Oct 2026

Rollout-LaSDI: Enhancing the long-term accuracy of Latent Space Dynamics

arXiv 2509.08191 ↗First posted 9 Sep 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Solving complex partial differential equations is vital in the physical sciences, but often requires computationally expensive numerical methods. Reduced-order models (ROMs) address this by exploiting dimensionality reduction to create fast approximations. While modern ROMs can solve parameterized families of PDEs, their predictive power degrades over long time horizons. We address this by (1) introducing a flexible, high-order, yet inexpensive finite-difference scheme and (2) proposing a Rollout loss that trains ROMs to make accurate predictions over arbitrary time horizons. We demonstrate our approach on the 2D Burgers equation.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 29 references that are in the map. First posted on arXiv 9 Sep 2025.

Builds on

14 of 29 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020Universal Differential Equations for Scientific Machine Learningcited by 353
  5. 2017Sparse identification of nonlinear dynamics for model predictive control in the low-data limitcited by 140
  6. 2018Blessing of dimensionality: mathematical foundations of the statistical physics of datacited by 55
  7. 2022gLaSDI: Parametric Physics-informed Greedy Latent Space Dynamics Identificationcited by 30
  8. 2023GPLaSDI: Gaussian Process-based Interpretable Latent Space Dynamics Identification through Deep Autoencodercited by 30
  9. 2024tLaSDI: Thermodynamics-informed latent space dynamics identificationcited by 23
  10. 2024A Comprehensive Review of Latent Space Dynamics Identification Algorithms for Intrusive and Non-Intrusive Reduced-Order-Modelingcited by 22
  11. 2023Weak-Form Latent Space Dynamics Identificationcited by 20
  12. 2024Physics-informed active learning with simultaneous weak-form latent space dynamics identificationcited by 13
2 more
  1. 2023Data-Driven Autoencoder Numerical Solver with Uncertainty Quantification for Fast Physical Simulationscited by 3
  2. 2025mLaSDI: Multi-stage latent space dynamics identificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Higher-Order LaSDI: Reduced Order Modeling with Multiple Time Derivativescited by 2
  2. 2026Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Modelscited by 0