<html>
<head>
<meta http-equiv="content-type" content="text/html;
charset=ISO-8859-1">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<h4>CALL FOR ABSTRACTS AND OPEN PROBLEMS</h4>
<p>Resource-Efficient Machine Learning<br>
NIPS-2013 Workshop<br>
Tuesday, December 10, 2012<br>
Lake Tahoe, Nevada, US<br>
<a class="moz-txt-link-freetext"
href="https://sites.google.com/site/resefml2013">https://sites.google.com/site/resefml2013</a><br>
----------------------------------------------<br>
</p>
<p>We invite submission of abstracts and open problems to
Resource-Efficient Machine Learning NIPS-2013 workshop.<br>
</p>
<p> IMPORTANT DATES </p>
<p> <b>Submission Deadline:</b> October 9.<br>
<b>Notification of Acceptance:</b> October 23.</p>
More details are provided below.<br>
-----------------------------------------------
<h4>Abstract</h4>
Resource efficiency is key for making ideas practical. It is crucial
in many tasks, ranging from large-scale learning ("big data'') to
small-scale mobile devices. Understanding resource efficiency is
also important for understanding biological systems, from individual
cells to complex learning systems, such as the human brain. The goal
of this workshop is to improve our fundamental theoretical
understanding and link between various applications of learning
under constraints on the resources, such as computation,
observations, communication, and memory. While the founding fathers
of machine learning were mainly concerned with characterizing the
sample complexity of learning (the observations resource) [VC74] it
now gets realized that fundamental understanding of other resource
requirements, such as computation, communication, and memory is
equally important for further progress [BB11]. <br>
<br>
The problem of resource-efficient learning is multidimensional and
we already see some parts of this puzzle being assembled. One
question is the interplay between the requirements on different
resources. Can we use more of one resource to save on a different
resource? For example, the dependence between computation and
observations requirements was studied in [SSS08,SSST12,SSB12].
Another question is online learning under various budget constraints
[AKKS12,BKS13,CKS04,DSSS05,CBG06]. One example that Badanidiyuru et
al. provide is dynamic pricing with limited supply, where we have a
limited number of items to sell and on each successful sale
transaction we lose one item. A related question of online learning
under constraints on information acquisition was studied in
[SBCA13], where the constraints could be computational or monetary.
Yet another direction is adaptation of algorithms to the complexity
of operation environment. Such adaptation can allow resource
consumption to reflect the hardness of a situation being faced. An
example of such adaptation in multiarmed bandits with side
information was given in [SAL+11]. Another way of adaptation is
interpolation between stochastic and adversarial environments. At
the moment there are two prevailing formalisms for modeling the
environment, stochastic and adversarial (also known as ``the average
case'' and ``the worst case''). But in reality the environment is
often neither stochastic, nor adversarial, but something in between.
It is, therefore, crucial to understand the intermediate regime.
First steps in this direction were done in [BS12]. And, of course,
one of the flagman problems nowadays is ``big data'', where the
constraint shifts from the number of observations to computation. We
strongly believe that there are deep connections between problems at
various scales and with various resource constraints and there are
basic principles of learning under resource constraints that are yet
to be discovered. We invite researchers to share their practical
challenges and theoretical insights on this problem. <br>
<br>
Study of resource-efficient learning also require design of
resource-dependent performance measures. In the past, algorithms
were compared in terms of predictive accuracy (classification
errors, AUC, F-measures, NDCG, etc.), yet there is a need to
evaluate them with additional metrics related to resources, such as
memory, CPU time, and even power. For example, reward per
computational operation. This theme will also be discussed at the
workshop. <br>
<br>
References:<br>
[AKKS12] Kareem Amin, Michael Kearns, Peter Key and Anton
Schwaighofer. Budget Optimization for Sponsored Search: Censored
Learning in MDPs. UAI 2012. <br>
[BB11] Leon Bottou and Olivier Bousquet. The trade-offs of large
scale learning. In Suvrit Sra, Sebastian Nowozin, and Stephen J.
Wright, editors, Optimization for Machine Learning. MIT Press, 2011.
<br>
[BKS13] Ashwinkumar Badanidiyuru, Robert Kleinberg and Aleksandrs
Slivkins. Bandits with Knapsacks. FOCS, 2013.<br>
[BS12] Sebastien Bubeck and Aleksandrs Slivkins. The best of both
worlds: stochastic and adversarial bandits. COLT, 2012.<br>
[CBG06] Nicolò Cesa-Bianchi and Claudio Gentile. Tracking the best
hyperplane with a simple budget perceptron. COLT 2006. <br>
[CKS04] Koby Crammer, Jaz Kandola and Yoram Singer. Online
Classification on a Budget. NIPS 2003. <br>
[DSSS05] Ofer Dekel, Shai Shalev-shwartz and Yoram Singer. The
Forgetron: A kernel-based perceptron on a fixed budget. NIPS 2004. <br>
[SAL+11] Yevgeny Seldin, Peter Auer, François Laviolette, John
Shawe-Taylor, and Ronald Ortner. PAC-Bayesian Analysis of Contextual
Bandits. NIPS, 2011. <br>
[SBCA13] Yevgeny Seldin, Peter Bartlett, Koby Crammer, and Yasin
Abbasi-Yadkori. Prediction with Limited Advice and Multiarmed
Bandits with Paid Observations. 2013. <br>
[SSB12] Shai Shalev-Shwartz and Aharon Birnbaum. Learning halfspaces
with the zero-one loss: Time-accuracy trade-offs. NIPS, 2012. <br>
[SSS08] Shai Shalev-Shwartz and Nathan Srebro. SVM Optimization:
Inverse Dependence on Training Set Size. ICML, 2008.<br>
[SSST12] Shai Shalev-Shwartz, Ohad Shamir, and Eran Tromer. Using
more data to speed-up training time. AISTATS, 2012.<br>
[VC74] Vladimir N. Vapnik and Alexey Ya. Chervonenkis. Theory of
pattern recognition. Nauka, Moscow (in Russian), 1974. German
translation: W.N.Wapnik, A.Ya.Tschervonenkis (1979), Theorie der
Zeichenerkennug, Akademia, Berlin.
<h4>Call for Sponsors</h4>
<p>Your logo could be here.... If you are interested to sponsor this
event, please, contact yevgeny.seldin at gmail.</p>
<h4>Call for Contributions</h4>
<p>We invite submission of <b>abstracts and open problems</b> to
the workshop. Abstracts and open problems should be at most 4
pages long in the <a
href="https://www.google.com/url?q=https%3A%2F%2Fnips.cc%2FPaperInformation%2FStyleFiles&sa=D&sntz=1&usg=AFrqEzcqzQaRgUcy_z9XvGI7PHaJrD5PXg">NIPS
format</a>. Appendices are allowed, but the organizers reserve
the right to evaluate the submissions based on the first 4 pages
only. Submissions should be NOT anonymous. Selected abstracts and
open problems will be presented as talks or posters during the
workshop. Contributions should be emailed to yevgeny.seldin at
gmail. </p>
<p> IMPORTANT DATES </p>
<p> <b>Submission Deadline:</b> October 9.<br>
<b>Notification of Acceptance:</b> October 23.</p>
<p>EVALUATION CRITERIA</p>
<ul>
<li>Theory and application-oriented contributions are equally
welcome.<br>
</li>
<li>All submissions should emphasize relevance to the workshop
subject.</li>
<li>Submission of previously published work or work under review
is allowed, in particular NIPS-2013 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!</li>
</ul>
<h4>Invited Speakers (tentative)<br>
</h4>
<a
href="http://www.google.com/url?q=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fpeople%2Fslivkins&sa=D&sntz=1&usg=AFrqEzcq8FiVZpP8SerrPSzCPitzRTgYeQ">Alexandrs
Slivkins</a>, Microsoft Research<br>
<a
href="http://www.google.com/url?q=http%3A%2F%2Fcs.stanford.edu%2Fpeople%2Fmmahoney%2F&sa=D&sntz=1&usg=AFrqEzeYfedlPRrUDeMnAtIRH26dbLoM-w">Michael
Mahoney</a>, Stanford
<h4>Organizers</h4>
<a
href="https://www.google.com/url?q=https%3A%2F%2Fsites.google.com%2Fsite%2Fyevgenyseldin&sa=D&sntz=1&usg=AFrqEzc2wzxGdoSn68PNkINqgCsvFMjQOA">Yevgeny
Seldin</a>, Queensland University of Technology and UC Berkeley<br>
<a
href="http://www.google.com/url?q=http%3A%2F%2Fwebee.technion.ac.il%2Fpeople%2Fkoby%2F&sa=D&sntz=1&usg=AFrqEzehNTgYPpJpcFJUST9hknRYFQhsRA">Koby
Crammer</a>, The Technion <br>
<a
href="http://www.google.com/url?q=http%3A%2F%2Fwebdocs.cs.ualberta.ca%2F%7Eabbasiya&sa=D&sntz=1&usg=AFrqEzfdCklx6ABkdZmZS7jyNsC9_TU_Fw">Yasin
Abbasi-Yadkori</a>, Queensland University of Technology and UC
Berkeley<br>
<a
href="http://www.google.com/url?q=http%3A%2F%2Fwww.herbrich.me&sa=D&sntz=1&usg=AFrqEzeyvu8HGZiis2YiBTE_xP3CD_kQ2w">Ralf
Herbrich</a>, Amazon<br>
<a
href="http://www.google.com/url?q=http%3A%2F%2Fwww.stat.berkeley.edu%2F%257Ebartlett%2F&sa=D&sntz=1&usg=AFrqEzfJ6kQ0KSL6vNMpQYruwRbVVxR1BA">Peter
Bartlett</a>, UC Berkeley and Queensland University of Technology
<h4>Schedule</h4>
TBA
</body>
</html>