SSA NSW Branch 2024 Annual Event with JB Douglas Award and Annual Lecture by Prof. Matt Wand

Please join us for the NSW SSA branch annual event on Thursday 14th November at the Sutherland Room, The University of Sydney from 3pm. The afternoon will start with presentations from PhD students from around NSW for the J. B. Douglas Awards. We are then proud to present our Annual Lecture by Distinguished Professor Matt Wand at 6pm, followed by the Annual dinner from 7pm.

We hope to see everyone there.

Program overview

7.00pm – Annual dinner, please register here by Thursday Nov 9th

Please click here for the JB Douglas Programme.

The location

The Sutherland Room is located at the Holmes Building, towards the northern side of the University of Sydney's Camperdown campus.

J. B. Douglas nominees

Ika Wulansari Discipline of Mathematical Sciences, UTS
Daniel Chee School of Mathematics and Statistics, UNSW Sydney
Jackson Zhou School of Mathematics and Statistics, University of Sydney
Hugh Entwistle School of Mathematical and Physical Sciences, Macquarie University
Bao Anh Vu National Institute for Applied Statistics Research Australia, University of Wollongong

Annual lecture

Speaker: Professor Matt Wand

Matt P. Wand is a Distinguished Professor of Statistics at the University of Technology Sydney. He has held faculty appointments at Harvard University, Rice University, Texas A&M University, the University of New South Wales and the University of Wollongong. Professor Wand is an elected fellow of the Australian Academy of Science, the American Statistical Association and the Institute of Mathematical Statistics. He was awarded two of the Australian Academy of Science's medals for statistical research: the Moran Medal in 1997 and the Hannan Medal in 2013. In 2014 he was awarded the Statistical Society of Australia's Pitman Medal. He has co-authored 3 books, more than 130 statistics journal articles and 10 R packages.

Title: Machine Learning Meets Likelihood Theory

Abstract:

Machine learning is a cousin of statistics that is concerned with the development of algorithms for learning from data. Examples of machine learning algorithms are artificial neural networks, reinforcement learning and expectation propagation. However, theory concerning statistical properties is scant. This lecture will provide a non-technical overview of the speaker's involvement in the evaluation of particular machine learning paradigms through the classical statistics prism of likelihood theory. For example, if expectation propagation is used for approximate fitting of a frequentist logistic mixed model then are the estimators of the model parameters asymptotically normal with Cramer-Rao lower bound variances? The lecture will also touch upon the following interesting side trip from this body of research: the derivation of new asymptotic normality results for exact maximum likelihood. The body of research goes back to the late 2000s and has involved leading Australian theoretical statisticians Peter Hall and Iain Johnstone, as well as several other Australia-based and U.S.A.-based statisticians.

Our Sponsors

If your organisation can sponsor a small amount, we would appreciate this. All sponsor logos will be displayed in the J.B. Douglas programme.

Australian Bureau of Statistics

uDASH, UNSW Sydney

The ARC Training Centre in Data Analytics for Resources and Environments, The University of Sydney

National Institute for Applied Statistics Research Australia, University of Wollongong

Stats Central, UNSW Sydney

School of Mathematical and Physical Sciences, Macquarie University

School of Mathematics and Statistics, UNSW Sydney

Please note that all our events are governed by the Code of Conduct. This means that we absolutely do not tolerate unacceptable behaviour, including any form of harassment. This applies to both members and non-members. If you have any concerns, please contact Gordana Popovic.

Any questions, please feel free to contact the NSW Branch Secretary.