Kalman filtering and smoothing solutions to temporal Gaussian process regression models
By Jouni Hartikainen, Simo Särkkä. 2010 IEEE International Workshop on Machine Learning for Signal Processing, 2010
304 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/ad49b47c51a0fc78b978ec8300d1fb04c4e962a8
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- G. Em Karniadakis
- Paris Perdikaris
- Maizar Raissi
- Yibo Yang
- Liu Yang
- Dongkun Zhang
- Arno Solin
- Alexander Grigorevskiy
In Statistical and Nonlinear Physics
- G. Em Karniadakis
- Paris Perdikaris
- Maizar Raissi
- Yibo Yang
- Liu Yang
- Lu Lu
- Ameya Dilip Jagtap
- Andrea Manzoni
Citations in the corpus
- State Space Gaussian Processes with Non-Gaussian Likelihood (2018, methodology): “For these time-series models, leveraging sequential state space methods from signal processing makes it possible to solve GP inference problems in linear time complexity O ( n ) if the underlying GP has Markovian structure (Reece & Roberts, 2010; Hartikainen & S ¨ arkk ¨ a, 2010).”
- Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations (2017, methodology): “In future work we plan to design more computationally efficient algorithms by exploring ideas including recursive Kalman updates [11] and variational inference [13].”
- Random Forests for dependent data (2020, background): “From [35], (`) admits a state-space representation:”
- Fast Direct Methods for Gaussian Processes (2014, methodology): “Thus, the development of a fast, accurate, and direct method is critical in making largescale Gaussian process modeling feasible.”
- Applied Stochastic Differential Equations (2019, unknown): “However, the spectral density of the squared exponential can be efficiently approximated by a Taylor expansion (see Hartikainen and Särkkä, 2010; Särkkä et al., 2013) or Padé approximants (Särkkä and Piché, 2014) which leads to a finite-dimensional SDE representation. In particular, as discussed in ”
- Hidden physics models: Machine learning of nonlinear partial differential equations (2017, methodology): “However, ideas such as recursive Kalman updates [32], variational inference [23], and parametric Gaussian processes [24] can be used to address this limitation.”