Special Session
Algebraic Geometry in Machine Learning 2012

6-8 February, 2012 - Vilamoura, Algarve, Portugal

Chair
Jason Morton, Pennsylvania State University, U.S.A.


Scope
The philosophy of algebraic statistics is that for many models arising in statistics and machine learning, the space of parameters or probability distributions modeled has the structure of an algebraic variety. This observation has led to new precise characterizations of popular models, new insights into representational power, and new approaches to studying learning performance (e.g. in the neighborhood of singularities, or proving the existence of a MLE).

For many classes of machine learning models, theoretical understanding has lagged behind experimental success. In many cases, representational power and performance characteristics are poorly understood, and even proponents are unsure why they work.
Understanding the algebraic, polyhedral, and tropical geometry of graphical models and other popular models has provided a new set of tools enabling researchers to settle several open questions about their capabilities, and progress on this front is expected to continue.

Topics for the special session may include the algebraic geometry and representation theory of machine learning models, the polyhedral and tropical geometry of the space of functions they can compute, geometric characterizations of architecture choice and asymptotic performance, and related topics.

Important Dates

Paper Submission: October 24, 2011
Authors Notification: November 11, 2011
Final Paper Submission and Registration: November 25, 2011

Paper Submission

Prospective authors are invited to submit papers in any of the topics listed above.
Instructions for preparing the manuscript (in Word and Latex formats) are available at:

Paper Templates

Please also check the Submission Guidelines.
Papers should be submitted electronically via the web-based submission system at: http://www.insticc.org/Primoris

Publications

All accepted papers (full, short and posters) will be published in a special section of the conference proceedings book - under an ISBN reference and on CD-ROM support - and submitted for indexation by Thomson Reuters Conference Proceedings Citation Index (ISI), INSPEC, DBLP and EI (Elsevier Index).
All papers presented at the conference venue will be available at the SciTePress Digital Library (http://www.scitepress.org/DigitalLibrary/). SciTePress is member of CrossRef (http://www.crossref.org/).

Secretariat Contacts

e-mail: icpram.secretariat@insticc.org
weblink: http://icpram.org/AGML.asp