Conference proceeding
Scalable and Robust Bayesian Inference via the Median Posterior
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), Vol.32, pp.1656-1664
Proceedings of Machine Learning Research
01/01/2014
Abstract
Many Bayesian learning methods for massive data benefit from working with small subsets of observations. In particular, significant progress has been made in scalable Bayesian learning via stochastic approximation. However, Bayesian learning methods in distributed computing environments are often problem- or distribution-specific and use ad hoc techniques. We propose a novel general approach to Bayesian inference that is scalable and robust to corruption in the data. Our technique is based on the idea of splitting the data into several non-overlapping subgroups, evaluating the posterior distribution given each independent subgroup, and then combining the results. Our main contribution is the proposed aggregation step which is based on finding the geometric median of subset posterior distributions. Presented theoretical and numerical results confirm the advantages of our approach.
Details
- Title: Subtitle
- Scalable and Robust Bayesian Inference via the Median Posterior
- Creators
- Stanislav Minsker - Duke UniversitySanvesh Srivastava - Duke UniversityLizhen Lin - Duke UniversityDavid B. Dunson - Duke University
- Contributors
- E P Xing (Editor)T Jebara (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), Vol.32, pp.1656-1664
- Publisher
- JMLR-JOURNAL MACHINE LEARNING RESEARCH
- Series
- Proceedings of Machine Learning Research
- ISSN
- 2640-3498
- Number of pages
- 9
- Grant note
- R01-ES-017436 / National Institute of Environmental Health Sciences (NIEHS) of the National Institutes of Health (NIH); United States Department of Health & Human Services; National Institutes of Health (NIH) - USA; NIH National Institute of Environmental Health Sciences (NIEHS) DMS-1127914; FODAVA CCF-0808847; DMS-0847388; ATD-1222567 / NSF; National Science Foundation (NSF)
- Language
- English
- Date published
- 01/01/2014
- Academic Unit
- Statistics and Actuarial Science
- Record Identifier
- 9984293099002771
Metrics
7 Record Views