On sparsity by NUV-EM, Gaussian message passing, and Kalman smoothing.
Hans-Andrea LoeligerLukas BrudererHampus MalmbergFederico WadehnNour ZalmaiPublished in: ITA (2016)
Keyphrases
- message passing
- maximum likelihood
- belief propagation
- gaussian mixture model
- linear quadratic
- expectation maximization
- gaussian distribution
- distributed systems
- graphical models
- em algorithm
- approximate inference
- factor graphs
- probabilistic model
- shared memory
- inference in graphical models
- markov random field
- kalman filter
- probabilistic inference
- generative model
- gaussian model
- parameter estimation
- mixture model
- junction tree
- distributed shared memory
- sum product algorithm
- ldpc codes
- matrix multiplication
- loopy belief propagation
- k means
- similarity measure
- gaussian noise
- image segmentation