Statistics Across Campuses: Multiple talks -- Statistics

Below are three talks running from 1pm: 

Friday 14 Aug 1pm, Dr Boris Beranger (UNSW Sydney) 
Composite likelihood and logistic regression models for aggregated data.  

Friday 14 Aug 2pm, Dr Khue-Dung Dang (UTS)
Subsampling Sequential Monte Carlo for Static Bayesian Models.  

Friday 14 Aug 4pm,
Dr Pavel Krupskiy (University of Melbourne) 
Conditional Normal Extreme-Value Copulas.  

Composite likelihood and logistic regression models for aggregated data 

Date: 14 August 2020, Friday 

Time: 1pm 

Speaker: Dr Boris Beranger (UNSW Sydney) 

Abstract: 

Symbolic data analysis (SDA) is an emerging technique for the analysis of large and
complex datasets where individual level data are summarised into group-based
distributional summaries (symbols) such as random rectangles or
histograms.Likelihood-based methods have been recently developed, allowing to fit models
for the underlying data while only observing distributional summaries.  However, while
powerful, when working with random histograms this approach rapidly becomes
computationally intractable as the dimension of the underlying data increases.  

In this talk we first introduce a composite likelihood setting for the analysis of
random histograms in K dimensions using lower-dimensional marginal histograms.  We apply
this approach to bypass the well known computational issues in the analysis of spatial
extremes over large number of spatial locations, and show large computational savings
compared to existing model fitting procedures.  

Logistic regression models are a popular method to predict the probability of
categorical response data.  However inference for these models can become
computationally prohibitive for large datasets.  The second part of the talk focuses on
summarising a collection of predictor variables into histograms in order to perform
inference.  Based on composite likelihoods, we derive an efficient one-versus rest
approximate composite likelihood model for histogram-value random variables.  We
demonstrate that this procedure can achieve comparable classification rates than
state-of-the-art subsampling algorithms for logistic regression.  

Link: https://zoom.uts.edu.au/j/91473507261 (Password: BayesStats) 

Subsampling Sequential Monte Carlo for Static Bayesian Models 

Date: 14th August 2020 Friday 

Time: 2-3pm 

Speaker: Dr.  Khue-Dung Dang (UTS) 

joint work David Gunawan, Matias Quiroz, Robert Kohn, and Minh Ngoc Tran 

Abstract: We show how to speed up Sequential Monte Carlo (SMC) for Bayesian inference in
large data problems by data subsampling.  SMC sequentially updates a cloud of particles
through a sequence of distributions, beginning with a distribution that is easy to
sample from such as the prior and ending with the posterior distribution.  Each update
of the particle cloud consists of three steps: reweighting, resampling, and moving.  In
the move step, each particle is moved using a Markov kernel; this is typically the most
computationally expensive part, particularly when the dataset is large.  It is crucial
to have an efficient move step to ensure particle diversity.  Our article makes two
important contributions.  First, in order to speed up the SMC computation, we use an
approximately unbiased and efficient annealed likelihood estimator based on data
subsampling.  The subsampling approach is more memory efficient than the corresponding
full data SMC, which is an advantage for parallel computation.  Second, we use a
Metropolis within Gibbs kernel with two conditional updates.  A Hamiltonian Monte Carlo
update makes distant moves for the model parameters, and a block pseudo-marginal
proposal is used for the particles corresponding to the auxiliary variables for the data
subsampling.  We demonstrate both the usefulness and limitations of the methodology for
estimating four generalized linear models and a generalized additive model with large
datasets.  

Zoom link: https://uow-au.zoom.us/j/96143600422?pwd=NGs3YUVpd244QndOcUt2Z1RyRmZOdz09 

Conditional Normal Extreme-Value Copulas 

Date: 14 August 2020, Friday 

Time: 4pm 

Speaker: Dr Pavel Krupskiy (University of Melbourne) 

Abstract: 

We propose a new class of extreme-value copulas which are extreme-value limits of
conditional normal models.  Conditional normal models are generalizations of conditional
independence models, where the dependence among observed variables is modeled using one
unobserved factor.  Conditional on this factor, the distribution of these variables is
given by the Gaussian copula.  This structure allows one to build flexible and
parsimonious models for data with complex dependence structures, such as data with
spatial or temporal dependence.  We study the extreme-value limits of these models and
show some interesting special cases of the proposed class of copulas.  We develop
estimation methods for the proposed models and conduct a simulation study to assess the
performance of these algorithms.  Finally, we applythese copula models to analyze data
on monthly wind maxima and stock return minima.  

Link: https://au.bbcollab.com/guest/fcf219c74ac743e89565a9e6e8d349a9