[Colloquium] Seminar Announcement: Recent Work on Interpretable Machine Learning

[Ninfa Mayorga via Colloquium]

Computation Institute Presentation - Data Lunch Seminar (DLS)

Speaker: Cynthia Rudin, Computer Science and Electrical and Computer Engineering, Duke University
Host:  Joseph Walsh
Date:  April 14, 2017
Time: 11:30 AM - 12:30 PM 
Location: The University of Chicago, Searle 240A, 5735 S. Ellis Ave.

Title: Recent Work on Interpretable Machine Learning

Abstract:
This issue of interpretability in predictive modeling is particularly important, given that the US government currently pays private companies for black box predictions that are used throughout the US Justice System. Do we really trust a black box model to make decisions on criminal justice? Propublica <https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing> showed that we should not. In particular, the black box predictions purchased by the US government are potentially biased. The US government could have tried to prove that no white box (interpretable) model exists that has the same accuracy, but they did not attempt that. For decisions of this gravity - for justice standards, healthcare, energy reliability or other critical infrastructure standards - it should be proven that no sufficient interpretable model exists before resorting to a black box.

In this talk I will discuss algorithms for interpretable machine learning. Some of these algorithms are designed to create proofs of nearness to optimality. I will focus on some of our most recent work, including 
(1) work on optimal rule list models using customized bounds and data structures (these are an alternative to CART) 
(2) work on optimal scoring systems (alternatives to logistic regression + rounding)

Since we have methods that can produce optimal or near-optimal models, we can use them to produce interesting new forms of interpretable models. These new forms were simply not possible before, since they are almost impossible to produce using traditional techniques (like greedy splitting and pruning).
In particular:
(3) Falling rule lists
(4) Causal falling rule lists
(5) Cost-effective treatment regimes

Work on (1) is joint with postdoc Elaine Angelino, students Nicholas Larus-Stone and Daniel Alabi, and colleague Margo Seltzer. Work on (2) is joint with student Berk Ustun. Work on (3) and (4) are joint with student Fulton Wang, and (5) is joint with student Himabindu Lakkaraju.

Bio:
Cynthia Rudin is an associate professor of computer science and electrical and computer engineering at Duke University, with secondary appointments in the statistics and mathematics departments. She directs the Prediction Analysis Lab. Her interests are in machine learning, data mining, applied statistics, and knowledge discovery (Big Data), and in particular, machine learning models that are interpretable to human experts. Her application areas are in energy grid reliability, healthcare, and computational criminology. Previously, Prof. Rudin held positions at MIT, Columbia, and NYU. She holds an undergraduate degree from the University at Buffalo where she received the College of Arts and Sciences Outstanding Senior Award in Sciences and Mathematics, and three separate outstanding senior awards from the departments of physics, music, and mathematics. She received a PhD in applied and computational mathematics from Princeton University. She is the recipient of the 2013 and 2016 INFORMS Innovative Applications in Analytics Awards, an NSF CAREER award, was named as one of the “Top 40 Under 40” by Poets and Quants in 2015, was named by Businessinsider.com <http://businessinsider.com/> as one of the 12 most impressive professors at MIT in 2015, and won an Adobe Digital Marketing Research Award in 2016. Her work has been featured in Businessweek, The Wall Street Journal, the New York Times, the Boston Globe, the Times of London, Fox News (Fox & Friends), the Toronto Star, WIRED Science, U.S. News and World Report, Slashdot, CIO magazine, Boston Public Radio, and on the cover of IEEE Computer. She serves on committees for DARPA, the American Statistical Association, INFORMS, the National Institute of Justice, and the National Academy of Sciences. She is past-chair of the INFORMS Data Mining Section, and is chair-elect of the Statistical Learning and Data Science section of the American Statistical Association.

Information:  Lunch will be provided

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20170414/5859ce24/attachment-0001.html>