Personal tools

Skip to content. | Skip to navigation

You are here: Home Conferences & Workshops Distributed machine learning and sparse representation with massive data sets

Distributed machine learning and sparse representation with massive data sets

— filed under:

Distributed machine learning and sparse representation with massive data sets (DMMD 2011)


The exponentially increasing demand for computing power as well as physical and economic limitations has contributed to a proliferation of distributed and parallel computer architectures. To make better use of current and future high-performance computing, and to fully benefit from these massive amounts of data, we must discover, understand and exploit the available parallelism in machine learning. Simultaneously, we have to model data in an adequate manner while keeping the models as simple as possible, by making use of a sparse representation of the data or sparse modelling of the respective underlying problem.



DMMD 2011 logo


Who Should Attend

  • Researchers in machine learning and statistics
  • Scientists from areas producing massive data sets, e.g. astronomy, energy, sensor networks
  • Parallel computing experts and practitioners
  • Curators of massive datasets or learning problems 


Registration required. Attendance is free but limited to approx. 50 participants (first in, best dressed).

To register, simply send an email to

Contact Information

Dr Oliver Obst
ICT Centre

Telephone: +61 2 9372 4710
Fax: +61 2 9372 4161


The program is now available as a PDF.

Call for Papers / Extended Abstracts

Through a combination of invited talks, contributed presentations, discussions and posters, we hope to gain a better understanding of available algorithms and best practices, as well as their inherent limitations.

Accepted submissions will be presented either as contributed talks or during the workshop poster discussion period. Submission should be extended abstracts, at most four pages long, in NIPS format (see instructions below).

Suggested topics include, but are not limited to:

  • Distributed, Multicore and Cluster based Learning Techniques
  • Machine Learning on Alternative Hardware (GPUs, Robots, Sensor Networks, Mobile Phones, Cell Processors ...)
  • Sparsity in Machine Learning and Statistics 
  • Learning results and techniques on Massive Datasets
  • Dimensionality Reduction, Sparse Matrix, Large Scale Kernel Methods
  • Fast Online Algorithms for Large Scale Data
  • Parallel Computing Tools and Libraries
Selected submissions will be considered for a special issue of a journal or a collected volume on the topic of the symposium. A separate call for papers will then be issued after the event for the special issue/collected volume.
We can not provide travel support, but for a limited (small) number of interstate/overseas students, we will organise free accommodation. Priority will be given to students with an accepted paper. If you would like to be considered for this, please send an email to apply (deadline 1 November 2010).

Invited Speakers

  • Samy Bengio (Google Research, CA, USA)
  • Barbara Hammer (University of Bielefeld, Germany)
  • Yann LeCun (New York University, NY, USA)
  • Michael Mahoney (Stanford University, CA, USA)


Important Dates

  • Submission deadline: 1 November, 2010
  • Registration deadline: 31 December, 2010
  • Symposium: 18-20 January, 2011


Funded by a CSIRO OCE Science Team Cutting Edge Science Symposium grant.

Organising chair: Oliver Obst.

Venue: Marsfield Lecture Theatre, Sydney.


Submission instructions

Submissions should be short papers / extended abstracts of at most 4 pages in length in NIPS format (please download a local copy of the NIPS 2010 template, or go to, and should include the title, authors' names, postal and email addresses, and an abstract not to exceed 150 words. Submissions in pdf format only should be sent to Oliver Obst with the subject line "DMMD 2011 Submission" and with the title, authors' names and abstract included in the body of the message.

Submissions will be reviewed by the program committee and selected submissions may be accepted either as a contributed talk or as a poster presentation. Please note submission of extended abstracts to DMMD 2011 does not preclude authors from submitting full versions of their work to conference or journal. 

Please note that one author of each accepted paper must present the paper at DMMD 2011.

If quality of submissions permits, a selection of contributions will be considered for a special issue / collected volume. Prospective authors will be notified, and a separate call for papers will be issued in this case. 


Program Committee


  • Samy Bengio (Google Research, CA, USA)
  • Joschka Boedecker (Osaka University, Japan)
  • Stephan Chalup (University of Newcastle, Newcastle)
  • Tim Cornwell (CSIRO CASS, Sydney)
  • Ying Guo (CSIRO ICT Centre, Sydney)
  • Barbara Hammer (University of Bielefeld, Germany)
  • Yann LeCun (New York University, NY, USA)
  • Simon Lucey (CSIRO ICT Centre, Sydney)
  • Michael Mahoney (Stanford University, CA, USA)
  • N. Michael Mayer (National Chung Cheng University, Taiwan)
  • Mikhail Prokopenko (CSIRO ICT Centre, Sydney)
  • Scott Sanner (NICTA & ANU, Canberra)
  • John A. Taylor (CSIRO CMIS, Canberra)
  • Rosalind Wang (CSIRO ICT Centre, Sydney)
  • TBA
Document Actions
Museum Robot

School students and others living in all corners of the country will soon have greater access to Australia's history, thanks to a CSIRO robot and high speed broadband connectivity. Read more...

Colin Griffith Apps Day spotlight

The Australian Centre for Broadband Innovation's first industry event demonstrated there is strong interest in driving innovation in broadband-enabled services. Read more...

Wifi Team

The CSIRO team that invented one of the foundation technologies of Wi-Fi has been named as a finalist in the European Inventor Award 2012. Read more