Mathematics Colloquia and Seminars

Return to Colloquia & Seminar listing

Current Approaches in Interpretable Machine Learning

Mathematics of Data & Decisions

Speaker: Cynthia Rudin, Duke (CS)
Related Webpage: https://users.cs.duke.edu/~cynthia/home.html
Location: Zoom Lecture
Start time: Tue, Oct 20 2020, 4:10PM

With widespread use of machine learning, there have been serious societal consequences from using black box models for high-stakes decisions, including flawed bail and parole decisions in criminal justice, flawed models in healthcare, and black box loan decisions in finance. Transparency and interpretability of machine learning models is critical in high stakes decisions. In this talk, I will focus on two of the most fundamental and important problems in the field of interpretable machine learning: optimal sparse decision trees and optimal scoring systems. I will also briefly describe work on interpretable neural networks for computer vision.

Optimal sparse decision trees: We want to find trees that maximize accuracy and minimize the number of leaves in the tree (sparsity). This is an NP hard optimization problem with no polynomial time approximation. I will present the first practical algorithm for solving this problem, which uses a highly customized dynamic-programming-with-bounds procedure, computational reuse, specialized data structures, analytical bounds, and bit-vector computations.

Optimal scoring systems: Scoring systems are sparse linear models with integer coefficients. Traditionally, scoring systems have been designed using manual feature elimination on logistic regression models, with a post-processing step where coefficients have been rounded. However, this process can fail badly to produce optimal (or near optimal) solutions. I will present a novel cutting plane method for producing scoring systems from data. The solutions are globally optimal according to the logistic loss, regularized by the number of terms (sparsity), with coefficients constrained to be integers. Predictive models from our algorithm have been used for many medical and criminal justice applications, including in intensive care units in hospitals.

Interpretable neural networks for computer vision: We have developed a neural network that performs case-based reasoning. It aims to explains its reasoning process in a way that humans can understand, even for complex classification tasks such as bird identification.

Papers:
Jimmy Lin, Chudi Zhong, Diane Hu, Cynthia Rudin, Margo Seltzer
Generalized and Scalable Optimal Sparse Decision Trees. ICML, 2020.

Berk Ustun and Cynthia Rudin
Learning Optimized Risk Scores. JMLR, 2019. Shorter version at KDD 2017.

Struck et al. Association of an Electroencephalography-Based Risk Score With Seizure Probability in Hospitalized Patients. JAMA Neurology, 2017.

Chaofan Chen, Oscar Li, Chaofan Tao, Alina Barnett, Jonathan Su, Cynthia Rudin
This Looks Like That: Deep Learning for Interpretable Image Recognition. NeurIPS, 2019.



zoom info available https://sites.google.com/view/maddd After the talk, we will do virtual tea/coffee get-together at https://gather.town/KOoFj0aKT5GkEj40/Alder-Room