CALL FOR ABSTRACTS AND OPEN PROBLEMS
Multi-Trade-offs in Machine Learning
NIPS-2012 Workshop, Lake Tahoe, Nevada, US
https://sites.google.com/site/multitradeoffs2012/
December 7 or 8, 2012
----------------------------------------------
We invite submission of abstracts and open problems to Multi-Trade-offs
in Machine Learning NIPS-2012 workshop.
IMPORTANT UPDATES:
*Deadline extension:* we are extending the deadline until October 16.
*Student scholarships:* we are grateful for receiving support from the
PASCAL network and will provide a limited number of travel scholarships
to students and post-docs. Detailed information will be published in a
few days on the web site.
IMPORTANT DATES
*Submission Deadline:* October 16.
*Notification of Acceptance:* October 30.
More details are provided below.
-----------------------------------------------
Abstract
One of the main practical goals of machine learning is to identify
relevant trade-offs in different problems, formalize, and solve them. We
have already achieved fairly good progress in addressing individual
trade-offs, such as model order selection or exploration-exploitation.
In this workshop we would like to focus on problems that involve more
than one trade-off simultaneously. We are interested both in practical
problems where "multi-trade-offs" arise and in theoretical approaches to
their solution. Obviously, many problems in life cannot be reduced to a
single trade-off and it is highly important to improve our ability to
address multiple trade-offs simultaneously. Below we provide several
examples of situations, where multiple trade-offs arise simultaneously.
The goal of the examples is to provide a starting point for a
discussion, but they are not limiting the scope and any other
multi-trade-off problem is welcome to be discussed at the workshop.
Multi-trade-offs arise naturally in interaction between multiple
learning systems or when a learning system faces multiple tasks
simultaneously; especially when the systems or tasks share common
resources, such as CPU time, memory, sensors, robot body, and so on. For
a concrete example, imagine a robot riding a bicycle and balancing a
pole. Each task individually (cycling and pole balancing) can be modeled
as a separate optimization problem, but their solutions has to be
coordinated, since they share robot resources and robot body. More
generally, each learning system or system component has its own internal
trade-offs, which have to be balanced against the trade-offs of other
systems, whereas shared resources introduce external trade-offs that
enforce cooperation. The complexity of interaction can vary from
independent systems sharing common resources to systems with various
degrees of relation between their inputs and tasks. In multi-agent
systems communication between the agents introduces an additional
trade-off.
We are also interested in multi-trade-offs that arise within individual
systems. For example, model order selection and computational complexity
[1], or model order selection and exploration-exploitation [2]. For a
specific example of this type of problems, imagine a system for
real-time prediction of the location of a ball in table tennis. This
system has to balance between at least three objectives that interact in
a non-trivial manner: (1) complexity of the model of flight trajectory,
(2) statistical reliability of the model, (3) computational
requirements. Complex models can potentially provide better predictions,
but can also lead to overfitting (trade-off between (1) and (2)) and are
computationally more demanding. At the same time, there is also a
trade-off between having fast crude predictions or slower, but more
precise estimations (trade-off between (3) and (1)+(2)). Despite the
complex nature of multi-trade-offs, there is still hope that they can be
formulated as convex problems, at least in some situations [3].
References:
[1] Shai Shalev-Shwartz and Nathan Srebro. "SVM Optimization: Inverse
Dependence on Training Set Size", ICML, 2008.
[2] Yevgeny Seldin, Peter Auer, François Laviolette, John Shawe-Taylor,
and Ronald Ortner. "PAC-Bayesian Analysis of Contextual Bandits", NIPS,
2011.
[3] Andreas Argyriou, Theodoros Evgeniou and Massimiliano Pontil. Convex
multi-task feature learning. Machine Learning, 2008, Volume 73, Number 3.
Call for Contributions
We invite submission of *abstracts and open problems* to the workshop.
Abstracts and open problems should be at most 4 pages long in the NIPS
format <https://nips.cc/PaperInformation/StyleFiles> (appendices are
allowed, but the organizers reserve the right to evaluate the
submissions based on the first 4 pages only). Selected abstracts and
open problems will be presented as talks or posters during the workshop.
Submission instructions will be published soon.
IMPORTANT DATES
*Submission Deadline:* October 16.
*Notification of Acceptance:* October 30.
EVALUATION CRITERIA
* Theory and application-oriented contributions are equally welcome.
* All the submissions should indicate clearly at least two non-trivial
trade-offs they are addressing.
* Submission of previously published work or work under review is
allowed, in particular NIPS-2012 submissions. However, for oral
presentations preference will be given to novel work or work that
was not yet presented elsewhere (for example, recent journal
publications or NIPS posters). All double submissions must be
clearly declared as such!
Invited Speakers
Shai Shalev-Shwartz <http://www.cs.huji.ac.il/%7Eshais/>, The Hebrew
University of Jerusalem
Jan Peters <http://www.ias.informatik.tu-darmstadt.de/Member/JanPeters>,
Technicsche Universitaet Darmstadt and Max Planck Institute for
Intelligent Systems
Csaba Szepesvari <http://www.ualberta.ca/%7Eszepesva/>, University of
Alberta
Organizers
Yevgeny Seldin <http://www.kyb.mpg.de/%7Eseldin>, Max Planck Institute
for Intelligent Systems and University College London
Guy Lever <http://www0.cs.ucl.ac.uk/people/G.Lever.html>, University
College London
John Shawe-Taylor <http://www0.cs.ucl.ac.uk/staff/j.shawe-taylor/>,
University College London
Koby Crammer <http://webee.technion.ac.il/people/koby/>, The Technion
Nicolò Cesa-Bianchi <http://homes.di.unimi.it/%7Ecesabian/>, Università
degli Studi di Milano
François Laviolette <http://www.ift.ulaval.ca/%7Elaviolette/>,
Université Laval (Québec)
Gábor Lugosi <http://www.econ.upf.edu/%7Elugosi/>, Pompeu Fabra University
Peter Bartlett <http://www.stat.berkeley.edu/%7Ebartlett/>, UC Berkeley
and Queensland University of Technology
Sponsors
We are grateful for receiving support from the PASCAL network.
If you would also like to sponsor this event, please, contact
[email protected].
Tentative Schedule
7:30 - 7:35 Opening remarks
7:35 - 8:20 Invited Talk
8:20 - 8:50 Two Contributed Talks
8:50 - 9:10 Break
9:10 - 9:55 Invited Talk
9:55 - 10:30 Open Problems Session
10:30 - 15:30 Break
15:30 - 16:15 Invited Talk
16:15 - 16:25 Break
16:25 - 17:00 Two Contributed Talks
17:00 - 18:30 Posters
18:30 - 19:00 Workshop Summary and Open Discussion
_______________________________________________
uai mailing list
[email protected]
https://secure.engr.oregonstate.edu/mailman/listinfo/uai
