OxCSML : People : Benjamin Bloem-Reddy

Bayesian nonparametrics, probabilistic modeling and inference

I am a Postdoctoral Research Assistant in Statistical Machine Learning. Previously, I completed my Ph.D. in Statistics at Columbia University, where I was advised by Peter Orbanz. My research focuses on probabilistic and statistical analysis of networks and other discrete data like partitions and permutations. I am generally interested in all aspects of machine learning, both theoretical and applied.

Publications

2019

B. Bloem-Reddy , Y. W. Teh , Probabilistic symmetry and invariant neural networks, Jan. 2019.

Project: bigbayes

@article{Bloem-Reddy:Teh:2019,
  archiveprefix = {arXiv},
  author = {Bloem-Reddy, Benjamin and Teh, Yee Whye},
  eprint = {1901.06082},
  month = jan,
  primaryclass = {stat.ML},
  title = {Probabilistic symmetry and invariant neural networks},
  year = {2019}
}

2018

B. Bloem-Reddy , A. Foster , E. Mathieu , Y. W. Teh , Sampling and Inference for Beta Neutral-to-the-Left Models of Sparse Networks, in Conference on Uncertainty in Artificial Intelligence, 2018.

Project: bigbayes

@inproceedings{BloemReddy:etal:2018,
  author = {Bloem-Reddy, Benjamin and Foster, Adam and Mathieu, Emile and Teh, Yee Whye},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  title = {Sampling and Inference for Beta Neutral-to-the-Left Models of Sparse Networks},
  month = aug,
  year = {2018}
}

B. Bloem-Reddy , P. Orbanz , Random-Walk Models of Network Formation and Sequential Monte Carlo Methods for Graphs, Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 80, no. 5, 871–898, Aug. 2018.

Project: bigbayes

@article{Bloem-Reddy:Orbanz:2018,
  archiveprefix = {arXiv},
  author = {Bloem-Reddy, Benjamin and Orbanz, Peter},
  eprint = {1612.06404},
  month = aug,
  primaryclass = {stat.ME},
  journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
  title = {Random-Walk Models of Network Formation and Sequential Monte Carlo Methods for Graphs},
  volume = {80},
  number = {5},
  pages = {871--898},
  year = {2018}
}

B. Bloem-Reddy , Y. W. Teh , Neural network models of exchangeable sequences, NeurIPS Workshop on Bayesian Deep Learning, 2018.

Project: bigbayes

@article{BloemReddy:Teh:2018aa,
  author = {Bloem-Reddy, Benjamin and Teh, Yee Whye},
  journal = {NeurIPS Workshop on Bayesian Deep Learning},
  title = {Neural network models of exchangeable sequences},
  year = {2018}
}

2017

B. Bloem-Reddy , P. Orbanz , Preferential Attachment and Vertex Arrival Times, Oct. 2017.

Project: bigbayes

@article{Bloem-Reddy:Orbanz:2017,
  archiveprefix = {arXiv},
  author = {Bloem-Reddy, Benjamin and Orbanz, Peter},
  eprint = {1710.02159},
  month = oct,
  primaryclass = {math.PR},
  title = {Preferential Attachment and Vertex Arrival Times},
  year = {2017}
}

B. Bloem-Reddy , Discussion of F. Caron and E. B. Fox, "Sparse graphs using exchangeable random measures.", Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 79, no. 5, 2017.

@article{BloemReddy:2017aa,
  author = {Bloem-Reddy, Benjamin},
  journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
  number = {5},
  title = {Discussion of F. Caron and E. B. Fox, "Sparse graphs using exchangeable random measures."},
  volume = {79},
  year = {2017}
}

B. Bloem-Reddy , E. Mathieu , A. Foster , T. Rainforth , H. Ge , M. Lomelí , Z. Ghahramani , Y. W. Teh , Sampling and inference for discrete random probability measures in probabilistic programs, NIPS Workshop on Advances in Approximate Bayesian Inference, 2017.
Project: bigbayes

We consider the problem of sampling a sequence from a discrete random probability measure (RPM) with countable support, under (probabilistic) constraints of finite memory and computation. A canonical example is sampling from the Dirichlet Process, which can be accomplished using its stick-breaking representation and lazy initialization of its atoms. We show that efficiently lazy initialization is possible if and only if a size-biased representation of the discrete RPM is used. For models constructed from such discrete RPMs, we consider the implications for generic particle-based inference methods in probabilistic programming systems. To demonstrate, we implement SMC for Normalized Inverse Gaussian Process mixture models in Turing.
```
@article{bloemreddy2017rpm,
  title = {Sampling and inference for discrete random probability measures in probabilistic programs},
  author = {Bloem-Reddy, Benjamin and Mathieu, Emile and Foster, Adam and Rainforth, Tom and Ge, Hong and Lomelí, María and Ghahramani, Zoubin and Teh, Yee Whye},
  journal = {NIPS Workshop on Advances in Approximate Bayesian Inference},
  year = {2017}
}
```

2016

B. Bloem-Reddy , J. P. Cunningham , Slice Sampling on Hamiltonian Trajectories, in International Conference on Machine Learning (ICML), 2016, vol. 33, 3050–3058.

@inproceedings{BloemReddy:Cunningham:2016,
  author = {Bloem-Reddy, Benjamin and Cunningham, John P.},
  booktitle = {International Conference on Machine Learning (ICML)},
  pages = {3050--3058},
  title = {Slice Sampling on Hamiltonian Trajectories},
  volume = {33},
  year = {2016}
}