Call for paper - ICML’2014 Workshop on New Learning Frameworks and Models for Big Data

23:00

Jeudi

Mar

2014

Conférence

http://ama.liglab.fr/nlfmbd_icml14/index.html

Équipes :

- Workshop organisé par l’équipe-action Khronos de PERSYVAL-Lab

- Pendant ICML’2014, à Beijing en Chine

- SUBMISSION

Please send to [email protected] by email in PDF or postscript in the ICML format the following :

A full paper 6-10 pages

In the body of your email, include (in plain ASCII) : names of all authors, their affiliations, their physical and email addresses and the track number which corresponds to your submission.

Submissions will be reviewed for technical soundness, relevance, significance and clarity by the organizing and review committee and invitations to present will be sent accordingly.

The full paper should be formatted according to the standard ICML templates available at : http://icml.cc/2014/icml2014stylefiles.zip and then converted to pdf or postscript.

- IMPORTANT DATES

Paper submission deadline : March 21, 2014
Notification of acceptance : April 18, 2014
Final camera ready submissions : May 5, 2014
Workshop : June 25, 2014

- ORGANIZERS

Massih-Reza Amini : Laboratoire d’Informatique de Grenoble, University of Grenoble
Rohit Babbar : Laboratoire d’Informatique de Grenoble, University of Grenoble
Éric Gaussier : Laboratoire d’Informatique de Grenoble, University of Grenoble
James Tin-Yau Kwok : Department of Computer Science and Engineering, Hong Kong
Ioannis Partalas : Laboratoire d’Informatique de Grenoble, University of Grenoble
Yiming Yang : School of Computer Science of Carnegie Mellon University

- PUBLICATION

Accepted papers will be put into a proposal for a publication with Cambridge Scholars.

- See the workshop Web page at : http://ama.liglab.fr/nlfmbd_icml14/index.htm

Huge amounts of data are now easily and legally available on the Web. This data is generally heterogeneous and merely structured. Machine learning models which have been developed to automatically retrieve, classify or cluster observations on large yet homogeneous data collections have to be rethought. Indeed, many challenging problems, inevitably associated to Big Data, have manifested the needs for tradeoffs between the two conflicting goals of speed and accuracy. This has led to some recent initiatives in both theory and practice and has highly motivated the interest of the Machine Learning community.

Further theoretical challenges include how to tackle problems with large number of target classes, appropriate optimization techniques to handle big data problems. Structured/sequential prediction models for big data problems such as prediction in hierarchy of classes has also gained importance in recent years.

The goal of this workshop is to bring together research studies aiming at developing new machine learning tools to handle new challenges associated to Big Data mining. We are especially interested on the following topics :

Distributed on-line learning
Multi-task learning for big data
Transfer Learning for big data
Optimization techniques for large-scale learning
Handling large number of target classes in big data
Structured prediction models in big data
Speed/Accuracy tradeoffs in big data
Statistical inference for big data
Noise in Big data

We see the workshop as a venue for the presentation of papers focusing on exploiting large scale data, but also as a forum for sharing ideas across different application domains. In particular it is an opportunity for discussion of techniques which are applicable to multiple types of datasets.