Edwin V. Bonilla

Prestigious Scientia Scholarships on Structured Prediction with Deep Learning

Applications are now open for the prestigious UNSW Scientia PhD Scholarship Scheme on the project Structured Prediction with Deep Learning under the supervision of Dr Edwin Bonilla.

The UNSW Scientia PhD Scholarship Scheme is the most prestigious and generous scholarship scheme at UNSW and it aims to attract the best and brightest people into strategic research areas. Awardees receive a $50,000 scholarship package for four years, comprising a $40,000 per annum tax-free stipend and a travel and development support package of up to $10,000 per annum. International students also receive a tuition fee scholarship.

In addition to this scholarship package, scholars are provided with access to a range of development opportunities across research, teaching and learning and leadership and engagement.

The successful applicant(s) will also be affiliated with the Australian Research Council (ARC) Centre of Excellence for Mathematical and Statistical Frontiers (ACEMS) and will be able to access the resources of ACEMS.

Applicants should submit their expression of interest here by 21st July 2017 but are encouraged to do so as early as possible.

More info about UNSW Scientia PhD Scholarship Scheme

More info about the project

Structured prediction is concerned with predicting multiple interdependent variables. This project will develop the fundamental science for the next generation of structured-prediction algorithms, which will have a significant impact on a large variety of applications, such as social graphs, natural language processing, action recognition and computational biology.

We will develop techniques for deep learning of features in structured prediction, along with Bayesian approaches for the characterisation and quantification of uncertainty. The immediate impact of these will be reflected in better accuracy of the resulting algorithms and in a significant reduction in the amount of annotated data they require for learning.

Example papers of the type of research I do can be found at my publications page. In particular, our recent work on Random Feature Expansions for Deep Gaussian Processes and Gray-box Inference for Structured Gaussian Process Models are strongly related to the aims of the project.

Supervisory Team

The successful applicant will be supervised by Dr. Edwin Bonilla, Scientia Prof. Robert Kohn and Associate Prof. Aleksandar Ignjatovic.


Feel free to contact me for more details.

Information for Potential PhD Students

If you are interested in doing a PhD in probabilistic machine learning at The University of New South Wales (UNSW) under my supervision please first read the following info:

If you have the necessary qualifications and background, feel free to contact me via email attaching the following documents in pdf format (I will disregard documents in any other format):

  • A CV.
  • A copy of your academic transcripts.
  • A brief statement of what area / problems you would like to work on.

You must have a strong math background and good programming skills. I will support your application as long as (a) you are indeed an outstanding student and (b) your project proposal  is aligned with my research interest (preferably in the areas of graphical models, nonparametric Bayesian methods, Gaussian processes, active learning of user preferences, Bayesian recommender systems).