Temporal Parallelization of Bayesian Smoothers

Simo Särkkä, Angel F. Garcıa-Fernandez

Research output: Contribution to journalArticle


This paper presents algorithms for temporal parallelization of Bayesian smoothers. We define the elements and the operators to pose these problems as the solutions to all-prefix-sums operations for which efficient parallel scan-algorithms are available. We present the temporal parallelization of the general Bayesian filtering and smoothing equations and specialize them to linear/Gaussian models. The advantage of the proposed algorithms is that they reduce the linear complexity of standard smoothing algorithms with respect to time to logarithmic.
Original languageEnglish
Number of pages8
JournalIEEE Transactions on Automatic Control
Publication statusE-pub ahead of print - 26 Feb 2020
MoE publication typeA1 Journal article-refereed


  • Bayesian smoothing
  • Kalman filtering and smoothing
  • Parallel computing
  • Prefix sums

Cite this