Workshop: Case Studies of Causal Discovery with Model Search

  Brain scan and causal chart

General Information

The Case Studies of Causal Discovery with Model Search Workshop is focused on applications of causal model search to science. It will include sessions on model search in Genetics, Biology, fMRI, Educational Research, Economics, and other disciplines.

Dates: October 25-27, 2013 (Friday-Sunday)
Location: Carnegie Mellon University, Pittsburgh, PA
The Friday sessions will take place in Rangos Hall (2nd floor, University Center)
The Saturday and Sunday sessions will take place in Baker Hall A53

Workshop Topic:
Computer scientists, statisticians, and philosophers have created a precise mathematical framework for representing causal systems called "Graphical Causal Models." This framework has supported the rigorous description of causal model spaces and the notion of empirical indistinguishability/equivalence within such spaces, which has in turn enabled computer scientists to develop asymptotically reliable model search algorithms for efficiently searching these spaces. The conditions under which these methods are practically useful in applied science is the topic of this workshop. The workshop will bring together scholars from genetics, biology, economics, fMRI-based cognitive neuroscience, climate research, education research, and several other disciplines, all of whom have successfully applied computerized search for causal models toward a scientifically challenging problem. The goals for the workshop are to: (1) to identify strategies for applying causal model search to diverse domain-specific scientific questions; (2) to identify and discuss methodological challenges that arise when applying causal model search to real-world scientific problems; and (3) to take concrete steps toward creating an interdisciplinary community of researchers interested in applied causal model search. We welcome junior scholars and graduate students, and we will host a free introductory tutorial on model search the first morning of the workshop.

Confirmed Speakers:

David Bessler (Economics, Texas A&M)
Frederick Eberhardt (Philosophy, Cal Tech)
Imme Ebert-Uphoff (Electrical & Computer Engineering, Colorado State University)
Kathleen Gates (Quantitative Psychology, University of North Carolina)
Clark Glymour (Philosophy, CMU)
Isabelle Guyon (ChaLearn, Berkeley, California)
Catherine Hanson (Psychology, Rutgers University)
Kevin Hoover (Economics and Philosophy, Duke University)
Marloes Maathuis (Statistics, ETH Zurich)
Alessio Moneta (Economics, Scuola Superiore Sant'Anna)
Sergey Plis (Mind Research Network and University of New Mexico)
Joseph Ramsey (Philosophy, CMU)
Martina Rau (Learning Sciences, Univ. of Wisconsin, Madison)
Karen Sachs (Stanford University School of Medicine)
Richard Scheines (Philosophy, CMU)
Cosma Shalizi (Statistics, CMU)
Bill Shipley (Biology, Sherbrooke University)
Alexander Statnikov (Health Informatics and Bioinformatics, New York University)
Ioannis Tsamardinos (Computer Science, University of Crete)


Friday, October 25
McKenna/Peter/Wright (University Center, 2nd floor) and Giant Eagle Auditorium (A51 Baker Hall)
McKenna/Peter/Wright (University Center, 2nd floor)
9:00-12:00 Tutorial on causal learning Richard Scheines   [Slides]
12:00-2:00 Lunch (on your own)
2:00-2:15 Introduction Richard Scheines    
2:15-3:00 Economics I David Bessler On Micro Economics I: The Use of TETRAD for Demand Specification [Video]
3:00-3:45 Economics II Kevin Hoover The Causal Structure of the Vector Autoregression in Economics: A Case Study [Slides]
3:45-4:15 Move to Baker Hall and coffee break
Giant Eagle Auditorium (A51 Baker Hall)
4:15-5:00 Economics III Alessio Moneta Causal model search applied to economics: gains, pitfalls and challenges [Slides]
5:00-5:45 State of the art Frederick Eberhardt All of causal discovery [Slides]
5:45-6:30 Causality workbench Isabelle Guyon Causality workbench [Video]
6:30- Dinner (on your own)
Saturday, October 26
Location: Baker Hall A53
9:00-9:45 fMRI I Joseph Ramsey & Clark Glymour Strategies for Discovering Mechanisms of Mind using fMRI [Slides]
9:45-10:30 fMRI II Catherine Hanson IMaGES in the Brain [Slides]
10:30-11:00 Coffee Break
11:00-11:45 fMRI III Kathleen Gates Approaches for accommodating two problems inherent in causal discovery searches on functional MRI data. [Video]
11:45-12:30 fMRI IV Sergey PlisBrain Connectivity Analysis: from Unimodal to Multimodal [Slides]
12:30-2:00 Lunch (on your own)
2:00-2:45 Understanding climate dynamics Imme Ebert-Uphoff Two applications of causal discovery in climate science [Video]
2:45-3:30 Biology I Bill Shipley The worldwide leaf economic spectrum: How causal discovery algorithms forced me to re-imagine its generating causes. [Slides]
3:30-4:00 Coffee break
4:00-4:30 Educational research I Richard Scheines Causal Models from Online Course and Tutor Logs [Slides]
4:30-5:00 Educational research II Martina Rau Searching for mediation models in intelligent tutoring systems data: representational understanding enhances representational fluency - but not vice versa [Slides]
5:00-6:30 Break
6:30- Workshop dinner: Schatz Dining Room, University Center, 2nd floor
Sunday, October 27
Location: Baker Hall A53
9:00-9:45 Genetics I Marloes Maathuis Learning gene regulatory networks: instability of constraint-based causal structure learning methods [Video]
9:45-10:30 Genetics II Alexander Statnikov Active Learning of Local Causal Pathways from High-Dimensional Data: New Methods and Empirical Comparison  
10:30-11:00 Coffee break
11:00-11:45 Genetics III Karen Sachs Biomolecular network models from single cell data [Video]
11:45-12:30 Biology II Ioannis Tsamardinos Causal Discovery from Mass Cytometry Data [Video]
12:30-2:30 Lunch and break-out sessions (catered)
2:30-3:15 Commentary/Response Cosma Shalizi    
3:15-4:00 Unsolved Problems Clark Glymour & Richard Scheines   [Video]


Registration is free. Please register for the workshop so we can estimate the number of attendees and plan accordingly: Click here to access the registration form


Travel Information:
Click here to see CMU's directions page for road directions, parking, and information on air, bus and rail transport to CMU.

Public transit to CMU from the airport:
The Pittsburgh International Airport is 22 miles from Carnegie Mellon. The Pittsburgh Port Authority runs the convenient 28X bus route from the airport. The 28X departs every 30 minutes and costs $3.75 (exact change is required). The route goes through downtown Pittsburgh and stops in front of CMU, taking about an hour (longer with traffic). Take the bus to the last stop, Morewood and Forbes Avenues. CMU is across the street.

Click here for the CMU campus map

Click here to see CMU's list of nearby accommodations

Workshop Organizers:
Richard Scheines
David Danks
Clark Glymour
Lizzie Silver

Please email Lizzie Silver for answers to logistics questions.
Address other questions to Richard Scheines.

Funding for this workshop was provided by the National Science Foundation, grant # SES1156001, and by the Center for Formal Epistemology at Carnegie Mellon University.