### Abstract

Many modern data analysis problems involve inferences from streaming data. However, streaming data is not easily amenable to the standard probabilistic modeling approaches, which require conditioning on finite data. We develop population variational Bayes, a new approach for using Bayesian modeling to analyze streams of data. It approximates a new type of distribution, the population posterior, which combines the notion of a population distribution of the data with Bayesian inference in a probabilistic model. We develop the population posterior for latent Dirichlet allocation and Dirichlet process mixtures. We study our method with several large-scale data sets.

Original language | English (US) |
---|---|

Pages (from-to) | 1153-1161 |

Number of pages | 9 |

Journal | Advances in Neural Information Processing Systems |

Volume | 2015-January |

State | Published - Jan 1 2015 |

### Fingerprint

### ASJC Scopus subject areas

- Computer Networks and Communications
- Information Systems
- Signal Processing

### Cite this

*Advances in Neural Information Processing Systems*,

*2015-January*, 1153-1161.

**The population posterior and Bayesian modeling on streams.** / McInerney, James; Ranganath, Rajesh; Blei, David.

Research output: Contribution to journal › Conference article

*Advances in Neural Information Processing Systems*, vol. 2015-January, pp. 1153-1161.

}

TY - JOUR

T1 - The population posterior and Bayesian modeling on streams

AU - McInerney, James

AU - Ranganath, Rajesh

AU - Blei, David

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Many modern data analysis problems involve inferences from streaming data. However, streaming data is not easily amenable to the standard probabilistic modeling approaches, which require conditioning on finite data. We develop population variational Bayes, a new approach for using Bayesian modeling to analyze streams of data. It approximates a new type of distribution, the population posterior, which combines the notion of a population distribution of the data with Bayesian inference in a probabilistic model. We develop the population posterior for latent Dirichlet allocation and Dirichlet process mixtures. We study our method with several large-scale data sets.

AB - Many modern data analysis problems involve inferences from streaming data. However, streaming data is not easily amenable to the standard probabilistic modeling approaches, which require conditioning on finite data. We develop population variational Bayes, a new approach for using Bayesian modeling to analyze streams of data. It approximates a new type of distribution, the population posterior, which combines the notion of a population distribution of the data with Bayesian inference in a probabilistic model. We develop the population posterior for latent Dirichlet allocation and Dirichlet process mixtures. We study our method with several large-scale data sets.

UR - http://www.scopus.com/inward/record.url?scp=84965175063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965175063&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84965175063

VL - 2015-January

SP - 1153

EP - 1161

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -