Forecasting high-dimensional dynamics exploiting suboptimal embeddings
Delay embedding---a method for reconstructing dynamical systems by delay coordinates---is widely used to forecast nonlinear time series as a model-free approach. When multivariate time series are observed, several existing frameworks can be applied to yield a single forecast combining multiple forecasts derived from various embeddings. However, the performance of these frameworks is not always satisfactory because they randomly select embeddings or use brute force and do not consider the diversity of the embeddings to combine. Herein, we develop a forecasting framework that overcomes these existing problems. The framework exploits various "suboptimal embeddings" obtained by minimizing the in-sample error via combinatorial optimization. The framework achieves the best results among existing frameworks for sample toy datasets and a real-world flood dataset. We show that the framework is applicable to a wide range of data lengths and dimensions. Therefore, the framework can be applied to various fields such as neuroscience, ecology, finance, fluid dynamics, weather, and disaster prevention.
Code (0)
등록된 구현이 없습니다.
Tasks
Combinatorial OptimizationDiversityTime SeriesTime Series AnalysisVocal Bursts Intensity PredictionSimilar Papers 제목 키워드 기반
Geometric Deep Learning for Realized Covariance Matrix Forecasting
Traditional methods employed in matrix volatility forecasting often overlook the inherent Riemannian manifold structure of symmetric positive definite matrices, treating them as elements of Euclidean space, which can lea…
Deep LearningFuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep forecasting models usually compress them into a unified end-to-end mappin…
Multivariate Time Series ForecastingOptimized Dynamic Mode Decomposition for Reconstruction and Forecasting of Atmospheric Chemistry Data
We introduce the optimized dynamic mode decomposition algorithm for constructing an adaptive and computationally efficient reduced order model and forecasting tool for global atmospheric chemistry dynamics. By exploiting…
Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting
Modern applications increasingly require learning and forecasting latent dynamics from high-dimensional time-series. Compared to univariate time-series forecasting, this adds a new challenge of reasoning about the latent…
Meta-LearningTime SeriesTime Series ForecastingUnivariate Time Series ForecastingGenerative Learning for Forecasting the Dynamics of Complex Systems
We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high …