Parallelizable sparse inverse formulation Gaussian processes (SpInGP)

• Published in: 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) pp. 1 - 6
• Main Authors: Grigorievskiy, Alexander, Lawrence, Neil, Sarkka, Simo
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2017
• Subjects: Computational modeling; Covariance matrices; Gaussian processes; Inference algorithms; Sparse matrices; Time complexity

We propose a parallelizable sparse inverse formulation Gaussian process (SpInGP) for temporal models. It uses a sparse precision GP formulation and sparse matrix routines to speed up the computations. Due to the state-space formulation used in the algorithm, the time complexity of the basic SpInGP i...