<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
This is probably the longest-reviewed paper ever submitted by an
Autonian!<br>
It feels like we were submitting it sometime a century ago :P<br>
<br>
But the ever-elusive GTC paper is finally out, and I am very proud
of Mathieu <br>
who persevered through this challenging experience!<br>
<br>
Cheers,<br>
Artur<br>
<br>
PS If this paper is setting the record for the amount of time spent
in the editor's hands,<br>
let us keep it this way and avoid challenging it with another
submission :)<br>
<br>
<div class="moz-cite-prefix">On 11/16/2017 2:15 PM, Lujie Chen
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:CAOQ-VV2=9qK+SL2w1v52JeJS1vK9w1dm-eBiXREgKFsz7w5VvA@mail.gmail.com">
<div dir="ltr">Finally saw it in press! <br>
<div>
<div class="gmail_quote">---------- Forwarded message
----------<br>
From: <b class="gmail_sendername">Charles Sutton</b> <span
dir="ltr"><<a href="mailto:production@jmlr.org"
moz-do-not-send="true">production@jmlr.org</a>></span><br>
Date: Thu, Nov 16, 2017 at 1:11 PM<br>
Subject: [Jmlr-announce] Classification of Time Sequences
using Graphs of Temporal Constraints<br>
To: <a href="mailto:jmlr-announce@csail.mit.edu"
moz-do-not-send="true">jmlr-announce@csail.mit.edu</a><br>
Cc: <a href="mailto:production@jmlr.org"
moz-do-not-send="true">production@jmlr.org</a><br>
<br>
<br>
The Journal of Machine Learning Research (<a
href="http://www.jmlr.org" rel="noreferrer"
target="_blank" moz-do-not-send="true">www.jmlr.org</a>)
is pleased to announce the publication of a new paper:<br>
------------------------------<wbr>------------------------------<wbr>------------------<br>
Classification of Time Sequences using Graphs of Temporal
Constraints<br>
Mathieu Guillame-Bert, Artur Dubrawski<br>
JMLR 18(121):1-34, 2017.<br>
Link: <a href="http://jmlr.org/papers/v18/15-403.html"
rel="noreferrer" target="_blank" moz-do-not-send="true">http://jmlr.org/papers/v18/15-<wbr>403.html</a><br>
<br>
Abstract<br>
We introduce two algorithms that learn to classify Symbolic
and Scalar Time Sequences (SSTS); an extension of
multivariate time series. An SSTS is a set of \emph{events}
and a set of <em>scalars</em>. An
<em>event</em> is defined by a symbol and a
time-stamp. A <em>scalar</em> is defined by a
symbol and a function mapping a number for each possible
time stamp of the data. The proposed algorithms rely on
temporal patterns called Graph of Temporal Constraints
(GTC). A GTC is a directed graph in which vertices express
occurrences of specific events, and edges express temporal
constraints between occurrences of pairs of events.
Additionally, each vertex of a GTC can be augmented with
numeric constraints on scalar values. We allow GTCs to be
cyclic and/or disconnected. The first of the introduced
algorithms extracts sets of co-dependent GTCs to be used in
a voting mechanism. The second algorithm builds decision
forest like representations where each node is a GTC. In
both algorit!<br>
hms, extraction of GTCs and model building are interleaved.
Both algorithms are closely related to each other and they
exhibit complementary properties including complexity,
performance, and interpretability. The main novelties of
this work reside in direct building of the model and
efficient learning of GTC structures. We explain the
proposed algorithms and evaluate their performance against a
diverse collection of 59 benchmark data sets. In these
experiments, our algorithms come across as highly
competitive and in most cases closely match or outperform
state-of-the-art alternatives in terms of the computational
speed while dominating in terms of the accuracy of
classification of time sequences.<br>
<br>
------------------------------<wbr>------------------------------<wbr>------------------<br>
This paper and previous papers are available electronically
at <a href="http://www.jmlr.org" rel="noreferrer"
target="_blank" moz-do-not-send="true">http://www.jmlr.org</a>
in PDF format. The papers of Volumes 1-4 were also published
in hardcopy by MIT Press; please see <a
href="http://mitpress.mit.edu/JMLR" rel="noreferrer"
target="_blank" moz-do-not-send="true">http://mitpress.mit.edu/JMLR</a>
for details. Volume 5 and subsequent volumes are being
printed in hardcopy by Microtome Publishing. Please see <a
href="http://www.mtome.com/Publications/JMLR/jmlr.html"
rel="noreferrer" target="_blank" moz-do-not-send="true">http://www.mtome.com/<wbr>Publications/JMLR/jmlr.html</a>
for details and ordering information.<br>
<br>
Charles Sutton<br>
<a href="mailto:production@jmlr.org" moz-do-not-send="true">production@jmlr.org</a><br>
<br>
______________________________<wbr>_________________<br>
Jmlr-announce mailing list<br>
<a href="mailto:Jmlr-announce@lists.csail.mit.edu"
moz-do-not-send="true">Jmlr-announce@lists.csail.mit.<wbr>edu</a><br>
<a
href="https://lists.csail.mit.edu/mailman/listinfo/jmlr-announce"
rel="noreferrer" target="_blank" moz-do-not-send="true">https://lists.csail.mit.edu/<wbr>mailman/listinfo/jmlr-announce</a><br>
</div>
<br>
<br clear="all">
<br>
-- <br>
<div class="gmail_signature" data-smartmail="gmail_signature">
<div dir="ltr">
<div>
<div dir="ltr">
<div>
<div dir="ltr">
<p><font face="arial, helvetica, sans-serif">==================</font></p>
<p><span
style="font-family:arial,helvetica,sans-serif;font-size:12.8px">Karen
(Lujie) Chen</span><br>
</p>
<font face="arial, helvetica, sans-serif">Ph.D.
Candidate in Information Systems, Heinz College</font></div>
<div dir="ltr"><span
style="font-family:arial,helvetica,sans-serif;font-size:12.8px">PIER
(Program of Interdisciplinary Educational
Research)</span><font face="arial, helvetica,
sans-serif"><br>
Member of Auton Lab, Robotics Institute</font></div>
<div dir="ltr"><font face="arial, helvetica,
sans-serif">Newell-Simon Hall 3124<br>
Carnegie Mellon University<br>
Pittsburgh, PA 15213</font>
<p><br>
</p>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</blockquote>
<br>
</body>
</html>