Indian buffet process
This article relies largely or entirely on a single source. (June 2017) |
In the mathematical theory of probability, the Indian buffet process (IBP) is a
Indian buffet process prior
Let be an binary matrix indicating the presence or absence of a latent feature. The IBP places the following prior on :
where is the number of non-zero columns in , is the number of ones in column of , is the -th harmonic number, and is the number of new dishes sampled by the -th customer. The parameter controls the expected number of features present in each observation.
In the Indian buffet process, the rows of correspond to customers and the columns correspond to dishes in an infinitely long buffet. The first customer takes the first dishes. The -th customer then takes dishes that have been previously sampled with probability , where is the number of people who have already sampled dish . He also takes new dishes. Therefore, is one if customer tried the -th dish and zero otherwise.
This process is infinitely exchangeable for an
See also
References
- T.L. Griffiths and Z. Ghahramani The Indian Buffet Process: An Introduction and Review, Journal of Machine Learning Research, pp. 1185–1224, 2011.