Corpus ID: 220041915

Slice Sampling for General Completely Random Measures

@article{Zhu2020SliceSF,
  title={Slice Sampling for General Completely Random Measures},
  author={Peiyuan Zhu and Alexandre Bouchard-C{\^o}t{\'e} and Trevor Campbell},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.13925}
}
  • Peiyuan Zhu, Alexandre Bouchard-Côté, Trevor Campbell
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • Completely random measures provide a principled approach to creating flexible unsupervised models, where the number of latent features is infinite and the number of features that influence the data grows with the size of the data set. Due to the infinity the latent features, posterior inference requires either marginalization— resulting in dependence structures that prevent efficient computation via parallelization and conjugacy—or finite truncation, which arbitrarily limits the flexibility of… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES

    Accelerated sampling for the Indian Buffet Process

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Combinatorial Clustering and the Beta Negative Binomial Process

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    MCMC for Normalized Random Measure Mixture Models

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    A moment-matching Ferguson & Klass algorithm