Estimating positive largest Lyapunov exponents from data is comparatively natural because neighboring trajectories separate, whereas stable dynamics require resolving contraction before measurement noise or finite precision erases the signal. We introduce a period-aware forecast-error contraction procedure for estimating a dominant negative Lyapunov exponent from ensembles of short scalar trajectories without using governing equations or an analytical Jacobian.
arXiv:2606. 01596v1 Announce Type: cross Abstract: Learning chaotic dynamical systems from data requires more than short-term predictive accuracy: the learned model must preserve the attractor geometry and its invariant statistics.
By Shinhoo Kang, Hai V. Nguyen, Tan Bui-Thanh
arXiv:2308. 08794v4 Announce Type: replace Abstract: Tipping points are abrupt, drastic, and often irreversible changes in the evolution of non-stationary and chaotic dynamical systems.
By Miguel Liu-Schiaffini, Clare E. Singer, Nikola Kovachki, Sze Chai Leung, Hyunji Jane Bae, Kamyar Azizzadenesheli, Anima Anandkumar
arXiv:2608. 16098v1 Announce Type: cross Abstract: Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces heterogeneous variables through an identical history-to-future map, whereas learning an independent predictor per variable restores flexibility at a cost that grows with the product of variable count, context length, and horizon.
By Xiachong Lin, Du Yin, Hao Xue, Wen Hu, Imran Razzak, Arian Prabowo, Matthew Amos, Flora D. Salim
arXiv:2606. 01894v1 Announce Type: new Abstract: Accurate Remaining Useful Life prediction is critical for industrial predictive maintenance.
By Deyu Zhuang, Peiliang Gong, Yang Shao, Liyuan Shu, Qi Zhu, Xiaoli Li, Daoqiang Zhang
Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, the parametrization is identified only up to equivalence, and every evaluation costs a pass over the entire series. Yet their moving-average term captures with a few parameters what a pure autoregression matches only with many lags.
arXiv:2608. 06340v1 Announce Type: cross Abstract: Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, the parametrization is identified only up to equivalence, and every evaluation costs a pass over the entire series.
By Daniel Paulin, Victor Elvira
arXiv:2602. 12756v2 Announce Type: replace Abstract: Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics.
By Xingyu Zhang, Jingyao Wang, Zeen Song, Changwen Zheng, Wenwen Qiang
arXiv:2505. 23863v3 Announce Type: replace-cross Abstract: Understanding chaotic dynamics is a fundamental problem across scientific disciplines, including climate science, neuroscience, and fluid dynamics, yet direct experimentation and intervention in such systems are often infeasible.
By Chang Liu, Bohao Zhao, Jingtao Ding, Huandong Wang, Yong Li
arXiv:2608. 16084v1 Announce Type: new Abstract: Neural autoregressive models have rapidly emerged as powerful emulators of high-dimensional chaotic systems, yet their long-term instability and error growth remain poorly understood, leading to ad-hoc solutions.
By Conrad Ainslie, Pedram Hassanzadeh, Michael W. Mahoney, Ashesh Chattopadhyay
arXiv:2607. 12928v1 Announce Type: new Abstract: We study the online binary sequential calibration problem.
By Zihan Zhang
arXiv:2601. 22328v2 Announce Type: replace Abstract: Real-world scientific systems are rarely observed through complete, regularly sampled state trajectories.
By Luca Muscarnera, Silas Ruhrberg Est\'evez, Samuel Holt, Evgeny Saveliev, Mihaela van der Schaar