A framework based on linear dynamical systems unifies fixed-point iteration schemes such as Newton, Picard, and Jacobi as approximate linearizations of nonlinear recursions for parallelizing sequential models.
The generative model of the LGSSM consists of dynamicsxt+1∼N(Axt,Q)and emissionsy t+1∼N(Hxt+1,R)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems
A framework based on linear dynamical systems unifies fixed-point iteration schemes such as Newton, Picard, and Jacobi as approximate linearizations of nonlinear recursions for parallelizing sequential models.