Workshop on Sparsity in Machine Learning and Statistics – Call for Papers

Workshop on Sparsity in Machine Learning and Statistics

Cumberland Lodge, UK
1 – 3 April 2009


Sparse estimation is playing an increasingly important role in the statistics and machine learning communities. Several methods have recently been developed in both fields, which rely upon the notion of sparsity (e.g.penalty methods like the Lasso, the Winnow algorithm, linear programming boosting, Dantzig selector, etc.), which can be thought of as a mathematical version of Occam’s razor. Many of the key theoretical ideas and statistical analysis of the methods have been developed independently, but there is increasing awareness of the potential for cross-fertilization of ideas between statistics and machine learning. Sparse estimation is starting to have an important impact on applied areas also, with applications ranging from biostatistics, medical imaging, to geoscience and finance. To bring together results on sparsity from different applied and theoretical fields of machine learning and statistics, we are planning to hold a workshop on 1-3rd April 2009 at Cumberland Lodge, UK.

The Invited Speakers include:
– Nicolò Cesa-Bianchi (Università degli Studi di Milano),
– Sara van de Geer (TBC) (ETH Zurich),
– Charles Micchelli (TBC) (State University of New York)
– Jared Tanner (University of Edinburgh),
– Alexandre Tsybakov (CREST and Université Paris VI),
– Jon Wellner (University of Washington),
– David Wipf (University of California),
– Ming Yuan (Georgia Tech College of Engineering),

and each invited speaker will give an hour long presentation, on different aspects of sparse estimation. In addition to the invited lectures there will be a number of contributed presentations, and a poster session. We invite you to submit a full page extended abstract, with pointers to reference material where appropriate. Submissions should be sent to and should be received by Thursday 15 January 2009. Notification of acceptance will be given on Friday 30 January 2009.

See also

Papers will be selected for oral or poster presentation.

Sofia Olhede, Massimiliano Pontil & John Shawe-Taylor

The GREAT08 Challenge

Will you be taking up the GRavitational lEnsing Accuracy Testing 2008
(GREAT08) PASCAL Challenge? The GREAT08 Challenge is an image analysis competition for gravitational lensing and cosmology, aimed at experts in statistical problems (including non-astronomers).

You can find more information here
There will be a videocon workshop on Monday 5th January 1-6pm GMT which will include an introduction to GREAT08.

Please sign up to the mailing list to receive important information by entering your address in the box at

If you have any questions then please contact me, or another member of the GREAT08 Team on

The GREAT08 Team

Post doctoral position in Machine Learning/Cognitive Vision/CBIR

For a project funded by the Austrian Science Foundation (FWF) and the European Commission, we are looking for a highly motivated post doctoral researcher with background in machine learning and/or cognitive vision and/or content based image retrieval. Among the possible fields of specialization are on-line learning, active learning, reinforcement learning, visual object classification, relevance feedback, and query-by-example search.

To learn more about the above project and the research at the Chair of Information Technology, University of Leoben, Austria, please visit

This position will be filled in January 2009 for the duration of 2 years (with a possible extension). Depending on your qualification salary is 30000-45000 EUR per year (after paying all social and insurance benefits and taxes this is net 1500-2000 EUR per month). Highly qualified PhD candidates may be considered as well.

Applicants should submit 1) a CV, including a brief research statement,
2) 1-3 recent publications in electronic format, and 3) the names and contact information of three individuals who can serve as references.


Univ.-Prof. Dr. Peter Auer
University of Leoben
Chair for Information Technology
Franz-Josef-Strasse 18, A-8700 Leoben, Austria
Fax: +43(3842)402-1502
E-mail: auer (at)

PASCAL Newsletter

The PASCAL newsletter contains all the latest updates, plus links to recently added publications and upcoming events.

December 2008

Junior Research Groups (W1/W2), Saarland University, Saarbruecken

Saarland University is seeking to establish several

Junior Research Groups (W1/W2)

within the recently established Cluster of Excellence “Multimodal Computing and Interaction” which was established by the German Research Foundation (DFG) within the framework of the German Excellence Initiative.

The term “multimodal” describes the different types of digital information such as text, speech, images, video, graphics, and high-dimensional data, and the way it is perceived and communicated, particularly through vision, hearing, and human expression. The challenge is now to organize, understand, and search this multimodal information in a robust, efficient and intelligent way, and to create dependable systems that allow natural and intuitive multimodal interaction. We are looking for highly motivated young researchers with a background in the research areas of the cluster, including algorithmic foundations, secure and autonomous networked systems, open science web, information processing in the life sciences, visual computing, large-scale virtual environments, synthetic virtual characters, text and speech processing and multimodal dialog systems. Additional information on the Cluster of Excellence is available on Group leaders will receive junior faculty status at Saarland University, including the right to supervise Bachelor, Master and PhD students. Positions are limited to five years.

Applicants for W1 positions (phase I of the program) must have completed an outstanding PhD. Upon successful evaluation after two years, W1 group leaders are eligible for promotion to W2. Direct applicants for W2 positions (phase II of the program) must have completed a postdoc stay and must have demonstrated outstanding research potential and the ability to successfully lead their own research group. Junior research groups are equipped with a budget of 80k to 100k Euros per year to cover research personnel and other costs.

Saarland University has leading departments in computer science and computational linguistics, with more than 200 PhD students working on topics related to the cluster (see for additional information). The German Excellence Initiative recently awarded multi-million grants to the Cluster of Excellence “Multimodal Computing and Interaction” as well as to the “Saarbrücken Graduate School of Computer Science”. An important factor to this success were the close ties to the Max Planck Institute for Computer Science, the German Research Center for Artificial Intelligence (DFKI), and the Max Planck Institute for Software Systems, which are co-located on the same campus.

Candidates should submit their application (curriculum vitae, photograph, list of publications, short research plan, copies of degree certificates, copies of the five most important publications, list of five references) to the coordinator of the cluster, Prof. Hans-Peter Seidel, MPI for Computer Science, Campus E1 4, 66123 Saarbrücken, Germany. Please, also send your application as a single PDF file to

The review of applications will begin on January 15, 2009, and applicants are strongly encouraged to submit applications by that date; however, applications will continue to be accepted until January 31, 2009. Final decisions will be made following a candidate symposium that will be held during March 9 – 13, 2009.

Saarland University is an equal opportunity employer. In accordance with its policy of increasing the proportion of women in this type of employment, the University actively encourages applications from women. For candidates with equal qualification, preference will be given to people with physical disabilities.

KDD 2009 Call for Research Papers

KDD-2009: The Fifteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’09)

Paris, France
June 28 – July 1, 2009.


The annual ACM SIGKDD conference is the premier international forum for data mining researchers and practitioners from academia, industry, and government to share their ideas, research results and experiences. KDD-09 will feature keynote presentations, oral paper presentations, poster sessions, workshops, tutorials, panels, exhibits, demonstrations, and the KDD Cup competition.

We invite submissions on all aspects of knowledge discovery and data mining. We especially encourage papers relevant to KDD that cut across disciplines such as machine learning, pattern recognition, statistics, databases, theory, mathematical optimization, data compression, cryptography, and high performance computing. Papers are expected to describe innovative ideas and solutions that are rigorously evaluated and well-presented. Submissions that describe minor variations of existing methods or only make small or questionable improvements to existing algorithms are discouraged.

Important dates:

***Note the earlier submission deadlines***
Abstract submission: February 2, 2009
Paper submission: February 6, 2009
Notification: April 10, 2009
Conference dates: June 28 – July 1, 2009

Areas of interest include, but are not limited to:

Novel data mining algorithms
Data mining foundations
Innovative applications of data mining
Data mining and KDD systems and frameworks Mining data streams and sensor data
Mining multi-media data
Mining social networks and graph data
Mining spatial and temporal data
Mining biological and biomedical data
Mining text, Web, semantic web and semi-structured data Mining dynamic data
Pre-processing and post-processing in data mining Robust and scalable statistical methods
Security, privacy, and adversarial data mining High performance and parallel/distributed data mining Mining tera-/peta-scale data
Visual data mining and data visualization Data integration issues in mining
Data and knowledge provenance in KDD

All submitted papers will be judged based on their technical merit, rigor, significance, originality, repeatability, relevance, and clarity. Papers submitted to KDD’09 should be original work, not previously published in a peer-reviewed conference or journal. Substantially similar versions of the paper submitted to KDD’09 should not be under review in another peer-reviewed conference or journal during the KDD-09 reviewing period.

Repeatability guideline:

Repeatability is a cornerstone of any scientific endeavor. To ensure the long term viability of the research output of the SIGKDD community, we require open-source/public distribution of the code and the datasets. In those cases where this is not possible due to proprietary considerations, every effort should be made to provide the binary executable. If proprietary datasets are used, every effort should also be made to apply the approach to similar publicly available datasets. Furthermore, the description of experimental results in submitted papers should be accompanied by all relevant implementation details and exact parameter specifications.

Peter Flach and Mohammed J. Zaki
KDD’09 Program Co-Chairs

John Elder and Francoise Soulie Fogelman General Chair

KDD-09 Call For Workshop Proposals

KDD-2009: The Fifteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’09)

Call for Workshop Proposals

Paris, France
June 28 – July 1, 2009

The ACM KDD-2009 organizing committee invites proposals for workshops to be held in conjunction with the conference. The purpose of a workshop is to provide participants with the opportunity to present and discuss novel research ideas on active and emerging topics of knowledge discovery and data mining. A workshop should also support the interaction and feedback among topic specialists from academia, industry and government.

A workshop may be organized around around industrial applications in a particular domain and the challenges this domain poses, such as the Netflix workshop on recommender systems (

A workshop may also include a challenge problem, such as the one on time series classification that took place in 2007 ( A session with papers that address a challenge complements the more diverse sessions with regular papers and improves the potential for discussion. Because such challenges require extra time to plan, we may
be willing to provide early notice of acceptance.

The organizers of approved workshops are required to announce the workshop and call for papers, gather submissions, conduct the reviewing process and decide upon the final workshop program. They must also prepare an informal set of workshop proceedings to be distributed with the registration materials at the conference. They may choose to form organizing or program committees for assistance in these tasks. The logistics of the workshops will be done with the help from the ACM KDD-2009 organizers.



* Workshop proposals due: Jan 19, 2009
* Notification of acceptance/rejection: Feb 13, 2009
* Deadline for camera ready workshop submissions: May 29, 2009


PROPOSAL DETAILS: Proposals should be no more than three pages in length and must include the

* Description of the workshop topic and the associated research issues
* Motivations why an ACM SIGKDD workshop on this topic should take place
* Description of the anticipated target group(s) of attendees
* Duration of the workshop (full day or half day)
* Contact information (address, email, and phone) for all organizers
* A designated contact person

The organizers are encouraged to provide the following additional information:

* Description of a potential challenge problem
* A preliminary list of reviewers
* One or more potential invited speakers
* A list of potential authors
* A list of potential attendees

Proposers are encouraged to have their drafts reviewed by potential workshop
participants before submission.

Workshop proposals should be sent by e-mail in either PDF/PS or ASCII format

the Workshop Chair: Carlos Soares,

General Chair: John Elder and Francoise Soulie Fogelman

Call for Papers: Machine Learning and Its Application Stream in the 23rd European Conference on Operational Research (EURO)

Machine Learning and Its Application” Stream in the 23rd European Conference on Operational Research (EURO), Bonn, Germany
July 5-8, 2009

Submission for abstracts starts: October 2008
Deadline for abstract submission: March 1, 2009
Notification of acceptance: March 31, 2009
Deadline for early registration: April 1, 2009
Deadline for author registration (for inclusion in the programme): April 15,2009
Conference: July 5-8, 2009

A subfield of Artificial Intelligence (AI), machine learning, is concerned with the development of algorithms that allow computers to “learn”. It is the process of training a system with a large number of examples, extracting rules and finding patterns in order to make predictions on new data points (examples). Common machine learning problems include supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, etc.. There are different kinds of applications in this field, including natural language processing, search engines, medical diagnosis, bioinformatics, detecting credit card fraud, stock market analysis, classifying DNA sequences, speech and handwriting recognition, and object recognition in computer vision to name a few.

TOPICS OF INTEREST Topics of interest include, but are not limited to:

* Mathematical foundations of Learning Theory
* Data mining and machine learning algorithms and methods in OR areas
* Machine learning applications in Fraud Detection, Healthcare systems
* Optimization methods in machine learning
* Supervised and unsupervised learning methods and applications
* Clustering methods and its application to OR
* Kernel learning and its applications to OR, business, healthcare.

ABSTRACT SUBMISSION: Abstracts must be written in English and contain no more than 600 characters (no formulas or mathematical notations are allowed). Each attendee is allowed to present ONE paper at the conference. Abstract submissions can be done
( according to the guidelines posted there. At least one author of each accepted abstract is expected to participate in the conference and present his/her work.

PAPER SUBMISSION: We invite all researchers, academicians, practitioners, as well as students interested in all branches of operational research, mathematical modelling and economic analyses to participate in the conference and to present their papers in the following areas:

1. Continuous optimization and control
2. Data mining; knowledge discovery; artificial intelligence
3. DEA and performance management
4. Decision analysis; decision support systems; modelling languages
5. Discrete optimization; graphs & networks
6. Energy, environment & climate
7. Financial modelling; risk management; banking
8. Fuzzy sets; softcomputing
9. Game theory; mathematical & experimental economics
10. Health, life sciences & bioinformatics
11. Location; logistics; transportation; traffic
12. Metaheuristics & biologically inspired approaches
13. Multiple criteria decision making, optimization & group decision
14. OR education, history & ethics
15. OR for developing countries
16. OR in agriculture & natural resources
17. OR in industries & software applications
18. Production management; supply chain management
19. Revenue management & managerial accounting
20. Scheduling, time tabling & project management
21. Stochastic programming; stochastic modelling; simulation
22. System dynamics; dynamic modelling
23. Telecommunication & network analysis

Special Journal Issues:
European Journal of Operational Research Journal Organizacija

Kristiaan Pelckmans, University College London (UK)
Jacob Kogan, University of Maryland Baltimore County (USA)
Süreyya Özöðür-Akyüz, Middle East Technical University & Sabancý University(Turkey)

PhD student positions in Helsinki on mining and learning networks

Applications are invited for (up to) four-year fully-funded

PhD student positions

at the Department of Computer Science at the University of Helsinki, Finland. The selected students will receive well-supervised PhD training in a world-class research environment on the topics of data mining and machine learning. The starting date is flexible and to be negotiated, at the earliest March 1st 2009.

Specifically, the selected students will be working on methods for learning networks and graphs from a variety of data and utilizing the found structures for visualization, explanation, and prediction. The research will be carried out in the context of the Finnish Centre of Excellence for Algorithmic Data Analysis (Algodan) and the Helsinki Institute for Information Technology (HIIT). Students will be supervised by senior members of the recently established Discovering Network Structures (DiNS) collaboration:

– Jaakko Hollmen, chief research scientist
– Patrik Hoyer, academy research fellow
– Aapo Hyvarinen, professor
– Mikko Koivisto, academy research fellow
– Heikki Mannila, academy professor
– Petri Myllymaki, professor
– Juho Rousu, professor
– Hannu Toivonen, professor
– Esko Ukkonen, professor

Applications are welcome from candidates with a master’s degree or equivalent (students close to finishing can also apply) in a relevant quantitative topic, such as (for instance) computer science or statistics. Strong mathematical skills, adequate programming skills, and a good command of English are essential.

The salary for a starting doctoral student is based on level 2 of the demands level chart for teaching and research personnel. With the salary component based on personal work performance the overall starting salary is typically between 2000 – 2200 euros per month. There is no tuition fee at the university.

Applications with full contact information, a brief (one-page) statement of research interests, a CV and a transcript of studies (including all courses and grades) should be sent by email to Patrik Hoyer, All applications received no later than Dec 8th 2008 will receive equal and full consideration.

Finland has a high standard of living and a well-developed democratic welfare state, has been a member of the EU since 1995, and consistently ranks at or near the top in various international comparisons of national performance. English is widely spoken, particularly in Helsinki.

For further information please contact Prof. Heikki Mannila, +358 9 191 51246,, or see the DiNS project webpage and the links therein:

Further information on the research environment and on working in Finland:

One Research Fellow Position Available at RSISE@ANU

We are seeking an outstanding Research Fellow with excellent mathematical background and research expertise in

– Machine Learning or
– (Algorithmic) Information Theory or
– (Bayesian) Statistics or
– Artificial Intelligence or
– related area.

Possible backgrounds are a PhD, or near completion of a PhD, in mathematics, physics, computer science, engineering, or related. The initial appointment will be for 2-3 years.

The new employee will interact with Dr. Marcus Hutter and other people in the RSISE at the ANU.

Information for applicants:

Closing Date: 16 January 2009

The Australian National University (ANU) is located in the city of Canberra, the Federal Capital of Australia. The ANU consistently ranks top among all Universities in the southern hemisphere, third in the Asia/Pacific region, and in the top 50 worldwide.