Diffusion forecasting model with basis functions from QR-decomposition
From MaRDI portal
Abstract: The diffusion forecasting is a nonparametric approach that provably solves the Fokker-Planck PDE corresponding to It^o diffusion without knowing the underlying equation. The key idea of this method is to approximate the solution of the Fokker-Planck equation with a discrete representation of the shift (Koopman) operator on a set of basis functions generated via the diffusion maps algorithm. While the choice of these basis functions is provably optimal under appropriate conditions, computing these basis functions is quite expensive since it requires the eigendecomposition of an diffusion matrix, where denotes the data size and could be very large. For large-scale forecasting problems, only a few leading eigenvectors are computationally achievable. To overcome this computational bottleneck, a new set of basis functions constructed by orthonormalizing selected columns of the diffusion matrix and its leading eigenvectors is proposed. This computation can be carried out efficiently via the unpivoted Householder QR factorization. The efficiency and effectiveness of the proposed algorithm will be shown in both deterministically chaotic and stochastic dynamical systems; in the former case, the superiority of the proposed basis functions over purely eigenvectors is significant, while in the latter case forecasting accuracy is improved relative to using a purely small number of eigenvectors. Supporting arguments will be provided on three- and six-dimensional chaotic ODEs, a three-dimensional SDE that mimics turbulent systems, and also on the two spatial modes associated with the boreal winter Madden-Julian Oscillation obtained from applying the Nonlinear Laplacian Spectral Analysis on the measured Outgoing Longwave Radiation (OLR).
Recommendations
- Forecasting turbulent modes with nonparametric diffusion models: learning from noisy data
- Data-driven spectral decomposition and forecasting of ergodic dynamical systems
- A closed solution to the Fokker-Planck equation applied to forecasting
- Sample distribution function construction for non-stationary time-series forecasting
- Learning to Forecast Dynamical Systems from Streaming Data
Cites work
- A set of level 3 basic linear algebra subprograms
- An introduction to turbulent dynamical systems in complex systems
- Data-driven computational methods. Parameter and operator estimations
- Deterministic Nonperiodic Flow
- Diffusion maps
- Efficient data assimilation for spatiotemporal chaos: a local ensemble transform Kalman filter
- Elemental, a new framework for distributed memory dense matrix computations
- Forecasting turbulent modes with nonparametric diffusion models: learning from noisy data
- LAPACK Users' Guide
- Practical method for determining the minimum embedding dimension of a scalar time series
- Semiparametric modeling: correcting low-dimensional model error in parametric models
- Stochastic differential equations. An introduction with applications.
- Theory of Reproducing Kernels
- Variable bandwidth diffusion kernels
Cited in
(6)- Data-driven probability density forecast for stochastic dynamical systems
- Operator-theoretic framework for forecasting nonlinear time series with kernel analog techniques
- Geometric component analysis and its applications to data analysis
- A time-varying diffusion index forecasting model
- Forecasting turbulent modes with nonparametric diffusion models: learning from noisy data
- Forecasting Equations in Complex-Quaternionic Setting
This page was built for publication: Diffusion forecasting model with basis functions from QR-decomposition
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q722000)
