<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal"><b><span style="color:black">CausalML 2018 : ICML / IJCAI / AAMAS Workshop on Machine Learning for Causal Inference, Counterfactual Prediction, and Autonomous Action</span></b><span style="color:black"><o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black"><a href="https://sites.google.com/site/faim18wscausalml/"><span style="color:blue">https://sites.google.com/site/faim18wscausalml/</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black">July 15, 2018<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Stockholm, Sweden<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black">Many of the most impactful applications of machine learning are not just about prediction, but are about putting learning systems in control of selecting the right action at the right time. Examples of such systems
range from search engines that act by displaying a ranking, to medical decision support systems, recommender systems, ad placement systems, conversational systems, automated trading platforms, computer games, and cyber-physical systems like self-driving cars.
This focus on acting requires some causal understanding of the world, since actions are interventions that change the distribution of data unlike in standard prediction problems. This gives rise to challenging counterfactual and causal prediction problems.
However, causality is only a means to an end - namely being able to take the right actions; one typically does not have the burden of providing strong proofs of causal discovery. <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="color:black">Confirmed invited speakers</span></b><span style="color:black">: Alekh Agarwal, Victor Chernozhukov, Alexandra Chouldechova, Mohammad Ghavamzadeh, Jonas Peters, Suchi Saria, Csaba Szepesvari, Stefan Wager<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="color:black">We solicit submission of novel research</span></b><span style="color:black"> related to all aspects of causal inference, counterfactual prediction, and autonomous action. This includes, but is not limited to,
the following topics: <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Predicting counterfactual outcomes <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Estimation of (conditional) average treatment effects <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Contextual bandit algorithms and on-policy learning <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Batch/offline learning from bandit feedback <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Off-policy evaluation and learning <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Interactive experimental control vs. counterfactual estimation from logged experiments <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Online A/B-testing vs. offline A/B-testing <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- De-biasing observational data and feedback cycles <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Fairness of actions and causal aspects of fairness <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Applications in online systems (e.g. search, recommendation, ad placement) <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Applications in physical systems (e.g. cars, smart homes) <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">- Applications in medicine (e.g. personalized treatment, clinical trials) <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black">We suggest extended abstracts of 2 pages in ICML format, but no specific format is enforced. A maximum of 8 pages will be considered. References will not count towards the page limit. PDF files only. At the discretion
of the organizers, accepted contributions will be assigned slots as contributed talks and others will be presented as posters. <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="color:black">The deadline for submissions has been extended to</span></b><span style="color:black"><o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="color:black"><o:p> </o:p></span></b></p>
<p class="MsoNormal" style="text-indent:.5in"><b><span style="color:black">May 23, 2018</span></b><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black">Submissions via <a href="https://sites.google.com/site/faim18wscausalml/">
<span style="color:blue">https://sites.google.com/site/faim18wscausalml/</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Author notification: May 30,2018<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black">As part of the workshop, we are organizing a CrowdAI competition on learning from logged contextual bandit feedback with non-uniform action-selection propensities. The data is provided by Criteo, and a separate
announcement is forthcoming. The winners will be invited to present their approach at the workshop. <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:black">Organizers<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Clement Calauzenes (Criteo) <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Thorsten Joachims (Cornell) <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Nathan Kallus (Cornell) <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Adith Swaminathan (Microsoft Research) <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Philip Thomas (UMass Amherst) <o:p></o:p></span></p>
<p class="MsoNormal">---<o:p></o:p></p>
<p class="MsoNormal">Thorsten Joachims<o:p></o:p></p>
<p class="MsoNormal">Chair, Department of Information Science<o:p></o:p></p>
<p class="MsoNormal">Professor, Department of Computer Science<o:p></o:p></p>
<p class="MsoNormal">Cornell University<o:p></o:p></p>
<p class="MsoNormal"><a href="http://www.joachims.org/"><span style="color:blue">http://www.joachims.org/</span></a><o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>