<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div class="">Everyone,</div><div class=""><br class=""></div><div class="">This is a final reminder that submissions for our ICML 2017 Workshop on Deep Structured Prediction are due this Friday. See the full CFP below, now with a list of great invited speakers that will continue to grow.</div><div class=""><br class=""></div><div class="">Bert</div><div class=""><br class=""></div><div class=""><div>--</div><div>Bert Huang, Ph.D. </div><div>Assistant Professor</div><div>Dept. of Computer Science, Virginia Tech</div><div><a href="http://berthuang.com" class="">http://berthuang.com</a></div></div><div><br class=""></div><div class="">******************************************************</div><div class=""><br class=""></div>Workshop of the International Conference on Machine Learning (ICML) 2017 Sydney, Australia 11 August 2017 Website: <a href="http://deepstruct.github.io/icml17" class="">http://deepstruct.github.io/icml17</a> <br class=""><br class="">TL;DR: 4 pages, in ICML format, submit by June 16 PT.<br class=""><br class="">Deep learning has revolutionized machine learning for many domains and problems. Today, most successful applications of deep learning involve predicting single variables (like univariate regression or multi-class classification). However, many real problems involve highly dependent, structured variables. In such scenarios, it is desired or even necessary to model correlations and dependencies between the multiple input and output variables. Such problems arise in a wide range of domains, from natural language processing, computer vision, computational biology and others.<br class=""><br class="">Some approaches to these problems directly use deep learning concepts, such as those that generate sequences using recurrent neural networks or that output image segmentations through convolutions. Others adapt the concepts from structured output learning. These structured output prediction problems were traditionally handled using linear models and hand-crafted features, with a structured optimization such as inference. It has recently been proposed to combine the representational power of deep neural networks with modeling variable dependence in a structured prediction framework. There are numerous interesting research questions related to modeling and optimization that arise in this problem space.<br class=""><br class="">The workshop will bring together experts in machine learning and application domains whose research focuses on combining deep learning and structured models. Specifically, it will provide an overview of existing approaches from various domains to distill from their success principles that can be more generally applicable. We will also discuss the main challenges arising in this setting and outline potential directions for future progress. The target audience consists of researchers and practitioners in machine learning and application areas.<br class=""><br class=""><b class="">Submissions</b><br class=""><br class="">We invite the submission of short papers no longer than four pages, including references, addressing machine learning research that intersects structured prediction and deep learning, including any of the following topics:<br class=""><br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Deep learning approaches for structured-output problems<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Integration of deep learning with structured-output learning<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• End-to-end learning of probabilistic models with non-linear potentials<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Deep learning applications with dependent inputs or outputs<br class=""><br class="">Papers should be formatted according to the ICML template: (<a href="http://media.nips.cc/Conferences/ICML2017/icml2017.tgz" class="">http://media.nips.cc/Conferences/ICML2017/icml2017.tgz</a>). Only papers using the above template will be considered. Word templates will not be provided.<br class=""><br class="">Papers should be submitted through easychair at the following address: <a href="https://easychair.org/conferences/?conf=1stdeepstructws" class="">https://easychair.org/conferences/?conf=1stdeepstructws</a> <br class=""><br class="">Papers will be reviewed for relevance and quality. Accepted papers will be posted online. Authors of high-quality papers will be offered oral presentations at the workshop, and we will award a best-paper and runner-up prize sponsored by Google.<br class=""><br class=""><b class="">Important Dates</b><br class=""><br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Abstracts deadline: June 16, 2017 PT<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Notification of acceptance: July 1, 2017<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Camera-ready deadline: August 1, 2017<br class=""><br class=""><div class=""><b class="">Confirmed invited speakers</b><br class=""><br class=""><div class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Ryan Adams, Harvard University<br class=""></div><div class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Raquel Urtasun, University of Toronto; Head of Uber ATG Toronto<br class=""></div><div class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Andrew McCallum, University of Massachusetts Amherst<br class=""></div><div class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Dhruv Batra, Georgia Tech / Facebook<br class=""></div><div class=""><br class=""></div><b class="">Program Committee</b><br class=""><br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• David Belanger, University of Massachusetts Amherst<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Matthew Blaschko, KU Leuven<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Ryan Cotterell, Johns Hopkins University<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Ming-Wei Chang, Microsoft Research<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Hal Daumé III, University of Maryland<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Justin Domke, University of Massachusetts Amherst<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• David Duvenaud, University of Toronto<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Daniel Lowd, University of Oregon<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Andrew McCallum, University of Massachusetts Amherst<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Eliyahu Kiperwasser, Bar-Ilan University<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Vitaly Kuznetsov, Google<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Kevin Murphy, Google<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Jason Naradowsky, University of Cambridge<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Sebastian Nowozin, Microsoft Research, Cambridge, UK<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Nanyun Peng, Johns Hopkins University<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Amirmohammad Rooshenas, University of Oregon<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Dan Roth, University of Illinois at Urbana-Champaign<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Alexander Rush, Harvard University<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Sameer Singh, University of California Irvine<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Uri Shalit, New York University<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Andreas Vlachos, University of Sheffield<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Yi Yang, Georgia Institute of Technology<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Scott Yih, Microsoft Research<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Yangfeng Ji, University of Washington<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Yisong Yue, California Institute of Technology<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Shuai Zheng, eBay<br class=""><br class=""><b class="">Organizers</b><br class=""><br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Isabelle Augenstein, University College London<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Kai-Wei Chang, University of California at Los Angeles<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Gal Chechik, Bar-Ilan University / Google<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Bert Huang, Virginia Tech<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Andre Martins, Unbabel and Instituto de Telecomunicacoes<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Ofer Meshi, Google<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Yishu Miao, University of Oxford<br class=""><span class="Apple-tab-span" style="white-space:pre"> </span>• Alexander Schwing, University of Illinois Urbana-Champaign<br class=""><br class=""></div><br class="">
<br class=""></body></html>