Call For Papers

Second Workshop on Tackling Computer Systems Problems
with Machine Learning Techniques (SysML07) 

In conjunction with NSDI 2007
April 10, 2007
Cambridge, MA USA

Many researchers in machine learning, systems, and networking have
begun to apply techniques from machine learning to help make
real-world computer systems and networks more robust and
manageable. Empirical models built using statistical learning have
great potential to help overcome the challenges of scale and
complexity in current and future systems.

The purpose of the SysML workshop is to bring together researchers
working at the intersection of machine learning and systems. It is
intended as a forum for researchers from different communities to
"cross-pollinate" and gain perspective on the hard problems and
opportunities, methodologies to evaluate learning-based approaches,
and the challenges of scaling up to larger, more complex, and more
dynamic systems.

Topics and submissions

We invite authors to submit position papers or reports of early work
related to current and future applications of machine learning
techniques to problems in computer systems.

Topics of interest include, but are not limited to:

- Use of machine learning techniques to address reliability,
  performance, security, or manageability issues in computer systems

- New applications of machine learning techniques to computer systems
  problems

- Challenges of scale in applying machine learning to large systems

- Experience with on-line data collection and machine learning
  analysis

- Integration of machine learning techniques into real-world systems
  and processes
 
We particularly encourage submissions describing experience with
real-world systems and lessons likely to be generally applicable
across a range of systems. Papers will be selected based on
originality, technical merit, topical relevance and their likelihood
of stimulating discussion at the workshop. Accepted papers will be
published on the workshop website, and a proceedings will be
distributed at the workshop.

Submission instructions 

Please submit papers in PDF format through the workshop website. The
page limit is 6 two-column pages (10pt font, 1 inch margins),
including all figures and references. The review process is
single-blind: please include the names of the authors and their
affiliations on the first page. Please do not submit previously
published material. Please do not submit material for simultaneous
review in multiple forums. Direct any questions to sysml07-chairs +
cs.duke.edu.

Submissions due: November 27, 2006 (midnight PST)
There is a 48-hour "amnesty" to modify submissions uploaded by the deadline.
Notification of acceptance: January 25, 2007
Final papers due: March 1, 2007
Workshop date: Tuesday, April 10, 2007

Program Committee

Jeff Chase, Duke University (co-chair) 
Ira Cohen, HP Labs (co-chair) 
Shivnath Babu, Duke University
Sumit Basu, Microsoft Research
George Forman, HP Labs
Armando Fox, UC Berkeley
Greg Ganger, CMU
Moises Goldszmidt, Microsoft Research 
Mike Jordan, UC Berkeley
Randy Katz, UC Berkeley
Emre Kiciman, Microsoft Research 
Irina Rish, IBM
Peter Stone, UT Austin
Gerald Tesauro, IBM
John Wroclawski, ISI

Steering Committee

Emre Kiciman, Microsoft Research 
Moises Goldszmidt, Microsoft Research