<div dir="ltr"><h3 style="line-height:1.38;text-align:justify;margin-top:14pt;margin-bottom:4pt"><span style="font-family:arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-weight:normal;font-size:11pt;color:rgb(0,0,0);vertical-align:baseline;white-space:pre-wrap">Apologies for cross-posting, we have extended the submission deadline for our workshop:</span></h3><h3 style="text-align:left;line-height:1.38;margin-top:14pt;margin-bottom:4pt"><span style="font-family:arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-weight:normal;font-size:11pt;color:rgb(0,0,0);vertical-align:baseline;white-space:pre-wrap">First Workshop "A <span class="gmail-il">causal</span> <span class="gmail-il">view</span> on dynamical systems" at NeurIPS 2022: </span><a href="https://sites.google.com/view/caudyn2022" target="_blank" style="font-family:arial,sans-serif;font-size:small;font-weight:normal;text-decoration-line:none"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;text-decoration-line:underline;vertical-align:baseline;white-space:pre-wrap">https://sites.google.com/<span class="gmail-il">view</span>/caudyn2022</span></a>, <span style="font-family:arial,sans-serif;background-color:transparent;color:rgb(0,0,0);font-size:11pt;white-space:pre-wrap;font-weight:normal">December 3, 2022, New Orleans, USA</span></h3><p dir="ltr" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><font face="arial, sans-serif"><span style="font-weight:bold;font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Submission deadline: </span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font color="#cc0000"><b>September 26, 2022 </b></font></span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">11:59 pm AoE</span></font></p><font face="arial, sans-serif"><br></font><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font face="arial, sans-serif">Topic and motivation</font></span></p><font face="arial, sans-serif"><br></font><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font face="arial, sans-serif">Multivariate time series are a common data modality in many scientific fields, such as physics, genomics, neuroscience or economics. A major goal in these disciplines is to answer <span class="gmail-il">causal</span> questions, such as gene regulatory network inference in biology or identifying <span class="gmail-il">causal</span> drivers of extreme (compound) weather events in climate science, which requires the inference of <span class="gmail-il">causal</span> relationships in dynamical systems. Similar to the static setting, accessibility, feasibility, and ethical considerations complicate direct experimentation and measurement of such relations in time-dependent settings. While certain properties of time series may aid practical <span class="gmail-il">causal</span> inference, such as the arrow of time, most identifiability results for <span class="gmail-il">causal</span> discovery as well as cause effect estimation are restricted to the static setting (as in structural <span class="gmail-il">causal</span> models or potential outcomes). These results typically do not extend to temporally evolving dynamics. Consequently, natural sciences mostly resort to continuous-time dynamical systems such as ODEs and PDEs to describe hypothesized mechanisms underlying the data generating processes. While such models also allow for <span class="gmail-il">causal</span> interpretations as well as predictions under hypothetical interventions, data-driven discovery of continuous-time dynamical systems remains a challenging and relatively underexplored area of research.</font></span></p><font face="arial, sans-serif"><br></font><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font face="arial, sans-serif">In this workshop, we bring together researchers in dynamical systems, time-series methods, <span class="gmail-il">causality</span>, infinite-depth neural networks, and machine learning. We believe a side-by-side discussion of dynamical systems and <span class="gmail-il">causal</span> inference (discovery and estimation) will allow one to develop novel approaches, transfer expertise across communities, and enable us to overcome current limitations of each individual <span class="gmail-il">perspective</span>. Connections to other scientific disciplines as well as practitioners’ <span class="gmail-il">view</span> will be highlighted to showcase successful applications of <span class="gmail-il">causal</span> inference in dynamical settings. </font></span></p><font face="arial, sans-serif"><br></font><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font face="arial, sans-serif">We welcome any contributions on ongoing research at the interface of <span class="gmail-il">causality</span> and dynamical systems, including but not limited to: </font></span></p><ul style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"><font face="arial, sans-serif"><span class="gmail-il">Causal</span> discovery in time-varying dynamical settings</font></span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"><font face="arial, sans-serif">Identification and estimation of <span class="gmail-il">causal</span> effects in dynamical systems</font></span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"><font face="arial, sans-serif">Granger <span class="gmail-il">causality</span></font></span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"><font face="arial, sans-serif">Data-driven discovery of dynamical laws (e.g. symbolic regression)</font></span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"><font face="arial, sans-serif">Deep learning for time-series modeling and prediction (e.g. neural ODEs)</font></span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"><font face="arial, sans-serif">Applications of dynamical modeling and <span class="gmail-il">causal</span> inference for scientific discovery</font></span></p></li></ul><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:12pt;margin-bottom:12pt"><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font face="arial, sans-serif">Important Dates</font></span></p><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:12pt;margin-bottom:12pt"><font face="arial, sans-serif"><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Paper submission deadline: </span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">September 22, 2022</span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><br></span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Notification to authors: October 20, 2022</span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><br></span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Camera-ready version: TBA</span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><br></span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Workshop date: December 3, 2022</span></font></p><p dir="ltr" style="line-height:1.2;text-align:justify;margin-top:12pt;margin-bottom:12pt"><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font face="arial, sans-serif">Submission instructions</font></span></p><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:12pt;margin-bottom:12pt"><font face="arial, sans-serif"><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">We invite submissions on on-going research that have not yet been published in a venue with proceedings. While we welcome unfinished work, submissions in this track should contain original ideas, connections, or results. The main body of the submission (including most important figures and tables) must not exceed 9 pages with unlimited additional space for references and supplementary material. Reviewers will be asked to judge the main body of the paper and will not be required to read the supplementary material. </span><span style="font-size:11pt;color:rgb(33,33,33);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Papers should be submitted anonymously to the OpenReview </span><a href="https://openreview.net/group?id=NeurIPS.cc/2022/Workshop/CDS&referrer=%5BHomepage%5D(%2F)" target="_blank" style="text-decoration-line:none"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;text-decoration-line:underline;vertical-align:baseline;white-space:pre-wrap">submission portal</span></a><span style="font-size:11pt;color:rgb(33,33,33);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"> as a single pdf formatted using </span><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">the </span><a href="https://docs.google.com/folderview?authuser=0&id=1sfn8-2BQfXYQkJjvR9w343XSyl7340w8" target="_blank" style="text-decoration-line:none"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;text-decoration-line:underline;vertical-align:baseline;white-space:pre-wrap">workshop’s latex style file</span></a><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">. All papers will undergo double-blind peer review based on which a subset will be invited for a contributed talk; all other accepted papers will be invited to be presented at the poster sessions. The workshop will not have proceedings.</span></font></p><p style="line-height:1.38;text-align:justify;margin-top:12pt;margin-bottom:12pt"><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><b><font face="arial, sans-serif">Invited speakers</font></b></span></p><font face="arial, sans-serif">Vanessa Didelez (University of Bremen)</font><div><span style="font-family:arial,sans-serif">Karl Friston (University College London)</span></div><div><span style="font-family:arial,sans-serif">Biwei Huang (UCSD)</span></div><div><font face="arial, sans-serif">Atalanti Mastakouri (Amazon)<br></font><span style="font-family:arial,sans-serif">Joris Mooij (University of Amsterdam)</span><font face="arial, sans-serif"><br>Cristopher Salvi (Imperial College London)</font><font face="arial, sans-serif"><br></font><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:12pt;margin-bottom:12pt"><span style="font-size:11pt;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><font face="arial, sans-serif">Organizers</font></span></p>Sören Becker (Helmholtz AI)<br>Alexis Bellot (DeepMind)<br>Cecilia Casolo  (Helmholtz AI)<br>Niki Kilbertus (TU Munich, Helmholtz AI)<br>Sara Magliacane (University of Amsterdam, MIT-IBM Watson AI Lab)<br>Yuyang (Bernie) Wang (AWS)</div></div>