Dependent Normalized Random Measures
dc.contributor.author | Chen, Changyou | |
dc.contributor.author | Rao, Vinayak | |
dc.contributor.author | Buntine, Wray | |
dc.contributor.author | Teh, Yee Whye | |
dc.coverage.spatial | Atlanta United States of America | |
dc.date.accessioned | 2015-12-10T23:19:59Z | |
dc.date.created | June 16-21 2013 | |
dc.date.issued | 2013 | |
dc.date.updated | 2015-12-10T10:19:28Z | |
dc.description.abstract | In this paper we propose two constructions of dependent normalized random measures, a class of nonparametric priors over dependent probability measures. Our constructions, which we call mixed normalized random measures (MNRM) and thinned normalized random measures (TNRM), involve (respectively) weighting and thinning parts of a shared underlying Poisson process before combining them together. We show that both MNRM and TNRM are marginally normalized random measures, resulting in well understood theoretical properties. We develop marginal and slice samplers for both models, the latter necessary for inference in TNRM. In time-varying topic modeling experiments, both models exhibit superior performance over related dependent models such as the hierarchical Dirichlet process and the spatial normalized Gamma process. | |
dc.identifier.uri | http://hdl.handle.net/1885/66136 | |
dc.publisher | MIT Press | |
dc.relation.ispartofseries | 30th International Conference on Machine Learning ICML 2013 | |
dc.source | The Sample-Complexity of General Reinforcement Learning | |
dc.source.uri | http://jmlr.org/proceedings/papers/v28/ | |
dc.title | Dependent Normalized Random Measures | |
dc.type | Conference paper | |
local.bibliographicCitation.lastpage | 9 | |
local.bibliographicCitation.startpage | 1 | |
local.contributor.affiliation | Chen, Changyou, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Rao, Vinayak, Duke University | |
local.contributor.affiliation | Buntine, Wray, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Teh, Yee Whye, University of Oxford | |
local.contributor.authoremail | u4814481@anu.edu.au | |
local.contributor.authoruid | Chen, Changyou, u4814481 | |
local.contributor.authoruid | Buntine, Wray, u1817485 | |
local.description.embargo | 2037-12-31 | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
local.identifier.absfor | 080199 - Artificial Intelligence and Image Processing not elsewhere classified | |
local.identifier.absseo | 970108 - Expanding Knowledge in the Information and Computing Sciences | |
local.identifier.ariespublication | u4334215xPUB1227 | |
local.identifier.scopusID | 2-s2.0-84897505920 | |
local.identifier.uidSubmittedBy | u4334215 | |
local.type.status | Published Version |
Downloads
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- 01_Chen_Dependent_Normalized_Random_2013.pdf
- Size:
- 424.56 KB
- Format:
- Adobe Portable Document Format