Initialization sometimes causes exponential scaling in runtime

ReactiveBayes / RxInfer.jl

Julia package for automated Bayesian inference on a factor graph with reactive message passing

https://rxinfer.ml/

MIT License

278 stars 23 forks source link

Closed bartvanerp closed 1 month ago

bartvanerp commented 2 months ago

See the original issue: https://github.com/biaslab/MultiAgentTrajectoryPlanning/issues/4 When increasing the loopyness in the model, the complexity scales very badly. Some messages are computed way more frequently, leading to large runtimes.

bvdmitri commented 1 month ago

Fixed in #354