Salīdzināt metodes

	Variacionālā inferenče ar trūkstošiem datiem	Gibsa paraugu ņemšana ar trūkstošiem datiem
Nozare	Bajesa metodes	Bajesa metodes
Saime	Bayesian methods	Bayesian methods
Izcelsmes gads	1994–2008	1987–1990
Autors	Ghahramani & Jordan; Wainwright & Jordan (formal foundations)	Tanner & Wong (data augmentation), Gelfand & Smith (Gibbs sampler)
Tips	Approximate Bayesian inference	Bayesian computational method
Pirmavots	Ghahramani, Z. & Jordan, M. I. (1994). Supervised learning from incomplete data via an EM approach. In Cowan, J. D., Tesauro, G. & Alspector, J. (Eds.), Advances in Neural Information Processing Systems 6 (pp. 120–127). Morgan Kaufmann.	Tanner, M. A. & Wong, W. H. (1987). The calculation of posterior distributions by data augmentation. Journal of the American Statistical Association, 82(398), 528–540.
Citi nosaukumi	VI with missing data, variational EM with missing data, VB missing data, mean-field VI for incomplete data	data augmentation Gibbs sampler, Gibbs sampler with data augmentation, Bayesian imputation via Gibbs sampling, MCMC missing data imputation
Saistītās	4	6
Kopsavilkums	Variational inference with missing data is a scalable Bayesian approach that simultaneously approximates the posterior over latent variables and model parameters while imputing missing observations. Instead of integrating over all possible values of the missing entries exactly, it posits a tractable approximate distribution and optimises it to be as close as possible to the true joint posterior, yielding fast, principled inference even in high-dimensional incomplete datasets.	Gibbs sampling with missing data treats unobserved values as additional unknowns alongside model parameters and samples all of them jointly within a Markov chain Monte Carlo loop. The method alternates between drawing the missing values from their conditional distribution given the parameters and drawing the parameters from their conditional distribution given the completed data, producing a posterior over both simultaneously.