REVIEW 6 cited by
Chaos as an interpretable benchmark for forecasting and data-driven modelling
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The striking fractal geometry of strange attractors underscores the generative nature of chaos: like probability distributions, chaotic systems can be repeatedly measured to produce arbitrarily-detailed information about the underlying attractor. Chaotic systems thus pose a unique challenge to modern statistical learning techniques, while retaining quantifiable mathematical properties that make them controllable and interpretable as benchmarks. Here, we present a growing database currently comprising 131 known chaotic dynamical systems spanning fields such as astrophysics, climatology, and biochemistry. Each system is paired with precomputed multivariate and univariate time series. Our dataset has comparable scale to existing static time series databases; however, our systems can be re-integrated to produce additional datasets of arbitrary length and granularity. Our dataset is annotated with known mathematical properties of each system, and we perform feature analysis to broadly categorize the diverse dynamics present across the collection. Chaotic systems inherently challenge forecasting models, and across extensive benchmarks we correlate forecasting performance with the degree of chaos present. We also exploit the unique generative properties of our dataset in several proof-of-concept experiments: surrogate transfer learning to improve time series classification, importance sampling to accelerate model training, and benchmarking symbolic regression algorithms.
Forward citations
Cited by 6 Pith papers
-
Attractor Geometry Determines the Identifiability Limits of System Discovery
The smallest eigenvalue of the attractor's invariant-measure moment matrix — not the choice of algorithm — sets the identifiability ceiling for recovering governing equations from trajectory data.
-
Fourier Weak SINDy: Spectral Test Function Selection for Robust Model Identification
Fourier Weak SINDy selects orthogonal sinusoidal test functions using multitaper spectral estimation to make weak-form SINDy robust and derivative-free for equation discovery in dynamical systems.
-
A Weak Penalty Neural ODE for Learning Chaotic Dynamics from Noisy Time Series
The Weak Penalty Neural ODE uses a weak form loss to filter noise and learn stable chaotic dynamics from noisy observations.
-
A tensor network approach for chaotic time series prediction
A tensor-network version of the truncated Volterra series predicts chaotic time series more accurately and trains faster than a conventional echo state network on 70 benchmark systems.
-
Learning with Mandelbrot and Julia
Seven off-the-shelf ML classifiers predict Mandelbrot and Julia membership from the first 1 to 4 orbit iterates and beat the matched-iterate escape-threshold rule on all tested benchmarks.
-
Sparse Identification of Nonlinear Dynamics with Conformal Prediction
Conformal prediction methods are integrated with Ensemble-SINDy to produce calibrated prediction intervals, feature importance measures, and coefficient uncertainty estimates for discovered dynamical system models.
Discussion (0). Sign in to comment.