News


Here you can find news about my professional life. Newest appear on top. You can also follow me on Twitter.

2019

2018

  • New publication (December): Our paper (with Ming Xu, Robert Kohn and Scott A. Sisson)  “Variance Reduction Properties of the Reparameterization Trick” has been accepted  for poster presentation and for publication in the conference proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019).

  • Our paper (with Khue-Dung Dang, Robert Kohn, Minh-Ngoc Tran and Mattias Villani). “Hamiltonian Monte Carlo with Energy Conserving Subsampling” has been significantly revised.
    Major change 1: Compares against SGLD and SG-HMC.
    Major change 2: Implements the block-Poisson estimator in a HMC context.

  • Slides from my talk at the ACEMS workshop.

  • I am a member of the Program Committee of the 12th International Conference on Monte Carlo Methods and Applications (MCM 2019).

  • I was awarded an Outstanding Achievement Recognition Award by the Australian Research Council Centre of Excellence for Mathematical and Statistical Frontiers.

  • I am reviewing for ICML 2019.

  • Our paper (with Ming Xu, Robert Kohn and Scott A. Sisson): “Variance reduction properties of the reparameterization trick” has been revised to fit an 8 pages conference format.

  • On November 30 I will give a talk at the ACEMS workshop “Advances and challenges in Monte Carlo methods” at the University of Queensland.

  • New paper on arXiv (with Ming Xu, Robert Kohn and Scott A. Sisson): “On Some Variance Reduction Properties of the Reparameterization Trick”.

  • New publication (September): Our paper (with Mattias Villani, Robert Kohn, Minh-Ngoc Tran and Khue-Dung Dang) “Subsampling MCMC – An Introduction for the Survey Statistician” has been accepted for publication in Sankhya A.

  • New paper on arXiv (with Mattias Villani, Robert Kohn, Minh-Ngoc Tran and Khue-Dung Dang): “Subsampling MCMC – A Review for the Survey Statistician”.

  • During Semester 2, I will teach the course ECON1203 – Business and Economics Statistics.

  • Slides from my talk in ISBA 2018.

  • Slides from my talk in EcoSta 2018.

  • Conference season is approaching! Come and see me present:
    Gaussian Variational Approximation for High-dimensional State Space Models at EcoSta 2018 on June 21, 08:30-10:10.
    The Block-Poisson Estimator for Optimally Tuned Exact Subsampling MCMC at ISBA 2018 on June 28, 17:30-19:00.

  • New paper on arXiv (with David Gunawan, Robert Kohn, Khue-Dung Dang and Minh-Ngoc Tran): “Subsampling Sequential Monte Carlo for Static Bayesian Models”.

  • Our paper (with David Nott and Robert Kohn): “Gaussian Variational Approximation for High-dimensional State Space Models” has been revised.

  • Our article “Speeding up MCMC by Delayed Acceptance and Data Subsampling” has now appeared in Journal of Computational and Graphical Statistics.

  • I am reviewing for NIPS 2018.

  • New version of our paper (with Minh-Ngoc Tran, Mattias Villani, Robert Kohn and Khue-Dung Dang)  “The Block-Poisson Estimator for Exact Subsampling MCMC”, which has the new title “The Block-Poisson Estimator for Optimally Tuned Exact Subsampling MCMC”.

  • Our paper (with Minh-Ngoc Tran, Mattias Villani, Robert Kohn and Khue-Dung Dang). “The Block-Poisson Estimator for Exact Subsampling MCMC” has been significantly revised.
    Note 1: Title has been changed from “Exact Subsampling MCMC”.
    Note 2: Methodological content of  The Block-Pseudo Marginal Sampler is now part of this paper.
    Note 3: New co-author Khue-Dung Dang.

  • On April 6 I will present our work on “Gaussian Variational Approximation for High-dimensional State Space Models” (arXiv) in the Mathematics of Biological Systems Management Symposium at the University of Melbourne. Slides from the talk.

  • New publication (February): Our paper (with Robert Kohn, Mattias Villani, and Minh-Ngoc Tran) “Speeding up MCMC by Efficient Data Subsampling” has been accepted for publication in the Journal of the American Statistical Association.

  • New paper on arXiv (with David Nott and Robert Kohn): “Gaussian Variational Approximation for High-dimensional State Space Models”.

  • During Semester 1, I will teach the course ECON1203 – Business and Economics Statistics.

  • I will be on vacations between January 2 – January 21.

2017

  • Our paper (with Robert Kohn, Mattias Villani, and Minh-Ngoc Tran) “Speeding up MCMC by Efficient Data Subsampling” has been revised.

  • On November 30 I presented some ongoing work (with David Nott and Robert Kohn) on Gaussian variational approximations at The Sydney Time Series & Forecasting Symposium. Paper soon to be ArXiv:ed.

  • Breaking news: I (my Bayesian alter ego) am on Twitter: MQBayes.

  • On November 13 I will present a poster on our paper (with Minh-Ngoc Tran, Robert Kohn and Mattias Villani) “The Block Pseudo-Marginal Sampler” at Bayes on the Beach.

  • On November 2 I gave a talk at the ACEMS yearly retreat on our project “Enabling Bayesian inference for big data”. Slides from the talk.

  • New paper on ArXiv (with Khue-Dung Dang, Robert Kohn, Minh-Ngoc Tran and Mattias Villani): “Hamiltonian Monte Carlo with Energy Conserving Subsampling”.

  • Our paper (with Mattias Villani, Robert Kohn, and Minh-Ngoc Tran) “Speeding up MCMC by Efficient Data Subsampling” has been revised.

  • I am assisting Robert Kohn in the course Econometric Theory and Methods.

  • On June 16 I will present our Exact Subsampling MCMC paper at the 1st International Conference on Econometrics and Statistics (EcoSta 2017)Slides from the talk.

  • On May 12 I will present our Exact Subsampling MCMC paper at the University of Sydney Business School’s seminar series. Slides from the talk.

  • I am reviewing for NIPS 2017.

  • New (and my first!) publication (March): Our paper (with Minh-Ngoc Tran, Mattias Villani and Robert Kohn) “Speeding up MCMC by Delayed Acceptance and Data Subsampling” has been accepted for publication in the Journal of Computational and Graphical Statistics.

  • Our paper (with Minh-Ngoc Tran, Robert Kohn and Mattias Villani) “The Block Pseudo-Marginal Sampler” has been revised. Note: Title has been changed from “Block-Wise Pseudo-Marginal Metropolis-Hastings”.

  • I am a Program Committee Member for ICML 2017.

  • New version of our paper (with Minh-Ngoc Tran, Mattias Villani and Robert Kohn) “Exact Subsampling MCMC”.

  • I have now (January 9) joined the School of Economics, UNSW Business School.

2016