mlsanityData to 14 Oct 2026

ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees

arXiv 2512.01984 ↗First posted 1 Dec 2025eess.SY cs.LG cs.SYcited by 2

Not on the map. Why?

Abstract (arXiv)

Chaos is a fundamental feature of many complex dynamical systems, including weather systems and fluid turbulence. These systems are inherently difficult to predict due to their extreme sensitivity to initial conditions. Many chaotic systems are dissipative and ergodic, motivating data-driven models that aim to learn invariant statistical properties over long time horizons. While recent models have shown empirical success in preserving invariant statistics, they are prone to generating unbounded predictions, which prevent meaningful statistics evaluation. To overcome this, we introduce the Energy-Constrained Operator (ECO) that simultaneously learns the system dynamics while enforcing boundedness in predictions. We leverage concepts from control theory to develop algebraic conditions based on a learnable energy function, ensuring the learned dynamics is dissipative. ECO enforces these algebraic conditions through an efficient closed-form quadratic projection layer, which provides provable trajectory boundedness. To our knowledge, this is the first work establishing such formal guarantees for data-driven chaotic dynamics models. Additionally, the learned invariant level set provides an outer estimate for the strange attractor, a complex structure that is computationally intractable to characterize. We demonstrate empirical success in ECO's ability to generate stable long-horizon forecasts, capturing invariant statistics on systems governed by chaotic PDEs, including the Kuramoto--Sivashinsky and the Navier--Stokes equations.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

14 of 35 references.

References · 14

  1. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  2. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  3. 2021Machine learning accelerated computational fluid dynamicscited by 471
  4. 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
  5. 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 134
  6. 2021On the difficulty of learning chaotic dynamics with RNNscited by 67
  7. 2024HardNet: Hard-Constrained Neural Networks with Universal Approximation Guaranteescited by 31
  8. 2023RAYEN: Imposition of Hard Convex Constraints on Neural Networkscited by 30
  9. 2024Physics-Informed Neural Networks with Hard Linear Equality Constraintscited by 30
  10. 2022POLICE: Provably Optimal Linear Constraint Enforcement for Deep Neural Networkscited by 19
  11. 2025ENFORCE: Nonlinear Constrained Learning with Adaptive-depth Neural Projectioncited by 17
  12. 2023Guaranteed Stable Quadratic Models and their applications in SINDy and Operator Inferencecited by 11
2 more
  1. 2025Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rulescited by 10
  2. 2023Data-Driven Control with Inherent Lyapunov Stabilitycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026LMI-Net: Linear Matrix Inequality--Constrained Neural Networks via Differentiable Projection Layerscited by 4
  2. 2026HardNet++: Nonlinear Constraint Enforcement in Neural Networkscited by 2