I’m giving a series of lectures this semester combining graphical models and some elements of nonparametric statistics. The intent is to build up to the theory of discrete matrix factorisation and its many variations. The lectures start on 27th July and are mostly given weekly. Weekly topics are given in the calendar.

## Archive for the ‘talks’ Category

## Lectures: Learning with Graphical Models

July 15, 2017## ICML 2017 paper: Leveraging Node Attributes for Incomplete Relational Data

May 19, 2017Here is a paper with Ethan Zhao and Lan Du, both of Monash, we’ll present in Sydney.

Relational data are usually highly incomplete in practice, which inspires us to leverage side information to improve the performance of community detection and link prediction. This paper presents a Bayesian probabilistic approach that incorporates various kinds of node attributes encoded in binary form in relational models with Poisson likelihood. Our method works flexibly with both directed and undirected relational networks. The inference can be done by efficient Gibbs sampling which leverages sparsity of both networks and node attributes. Extensive experiments show that our models achieve the state-of-the-art link prediction results, especially with highly incomplete relational data.

As usual, the reviews where entertaining, and some interesting results we didn’t get in the paper. Its always enlightening doing comparative experiments.

## ALTA 2016 Tutorial: Simpler Non-parametric Bayesian Models

April 21, 2017They recorded my tutorial ran at ALTA late in 2016.

Part 1 and part 2 up on Youtube, about an hour each.

## Visiting SMU in Singapore

November 23, 2016Currently visiting the LARC with Steven Hoi and will give a talk tomorrow on my latest work based on Lancelot James’ extensive theories of Bayesian non-parametrics.

**Simplifying Poisson Processes for Non-parametric Methods**

Main thing is I’ve been looking at hierarchical models, which have all their own theory, though easily developed using James’ general results. Not sure I’ll put the slides up because its not yet published!

## Talk at Data Science Meetup

April 4, 2016Today I’ll be giving a version of my “document analysis” grand tour talk to the Data Science Meetup in Melbourne. The slides for the talk in PDF are here. I also did a smaller version of one of my new graphics, this one on obesity. Needs to display for general viewers some distance away, so must be larger in perspective. The standard ones need a really big screen or you need to be up close!

## Introduction to Data Science Tutorial

December 27, 2015## Introduction to Data Science

November 7, 2015On 11th-14th January 2016 I’ll be visiting the School of IT at Monash University Malaysia, which is located within the Bandar Sunway township in Malaysia just outside Kuala Lumpur city. My talk should be on the Monday (11th). The slides are here (available temporarily).

**Title: Introduction to Data Science**

This 2 hour seminar works through some of the emerging highlights of Data Science, reviewing major videos, blogs and articles that helped mold the field. This seminar looks at processes and case studies to understand the many facets of working with data, and the significant effort in Data Science over and above the core task of Data Analysis. So the series is a broad introduction to working with data rather than a deep dive into the world of statistics. The seminar is aimed at those with an IT background who either want to start in Data Science or work with it, for instance in management or as a data engineer. Attendees should have a knowledge of information technology and computer science.

The talk will be extracted from our FIT5145 unit given in the Master of Data Science.