Optimal Explanations of Linear Models

When predictive models are used to support complex and important decisions, the ability to explain a model's reasoning can increase trust, expose hidden biases, and reduce vulnerability to adversarial attacks. However, attempts at interpreting models are often ad hoc and application-specific, and the concept of interpretability itself is not well-defined. We propose a general optimization framework to create explanations for linear models. Our methodology decomposes a linear model into a sequence of models of increasing complexity using coordinate updates on the coefficients. Computing this decomposition optimally is a difficult optimization problem for which we propose exact algorithms and scalable heuristics. By solving this problem, we can derive a parametrized family of interpretability metrics for linear models that generalizes typical proxies, and study the tradeoff between interpretability and predictive accuracy.

[1]  Joseph P. Simmons,et al.  Overcoming Algorithm Aversion: People Will Use Imperfect Algorithms If They Can (Even Slightly) Modify Them , 2016, Manag. Sci..

[2]  Alex Alves Freitas,et al.  Comprehensible classification models: a position paper , 2014, SKDD.

[3]  Cynthia Rudin,et al.  Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model , 2015, ArXiv.

[4]  D. Bertsimas,et al.  Best Subset Selection via a Modern Optimization Lens , 2015, 1507.03133.

[5]  Yair Zick,et al.  Algorithmic Transparency via Quantitative Input Influence , 2017 .

[6]  Lalana Kagal,et al.  Explaining Explanations: An Overview of Interpretability of Machine Learning , 2018, 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).

[7]  I. Y. Kim,et al.  Adaptive weighted-sum method for bi-objective optimization: Pareto front generation , 2005 .

[8]  Nada Lavrac,et al.  Selected techniques for data mining in medicine , 1999, Artif. Intell. Medicine.

[9]  Hadi Fanaee-T,et al.  Event labeling combining ensemble detectors and background knowledge , 2014, Progress in Artificial Intelligence.

[10]  Lalana Kagal,et al.  J un 2 01 8 Explaining Explanations : An Approach to Evaluating Interpretability of Machine Learning , 2018 .

[11]  D. Goldstein,et al.  Simple Rules for Complex Decisions , 2017, 1702.04690.

[12]  Rich Caruana,et al.  Model compression , 2006, KDD '06.

[13]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[14]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[15]  Cynthia Rudin,et al.  The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification , 2014, NIPS.

[16]  Osbert Bastani,et al.  Interpreting Blackbox Models via Model Extraction , 2017, ArXiv.

[17]  Jure Leskovec,et al.  Human Decisions and Machine Predictions , 2017, The quarterly journal of economics.

[18]  Sendhil Mullainathan,et al.  Does Machine Learning Automate Moral Hazard and Error? , 2017, The American economic review.

[19]  Richard A. Berk,et al.  An impact assessment of machine learning risk forecasts on parole board decisions and recidivism , 2017, Journal of Experimental Criminology.

[20]  Margo I. Seltzer,et al.  Scalable Bayesian Rule Lists , 2016, ICML.

[21]  Been Kim,et al.  Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[22]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[23]  Osbert Bastani,et al.  Interpreting Predictive Models for Human-in-the-Loop Analytics , 2018 .

[24]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[25]  Jure Leskovec,et al.  Interpretable & Explorable Approximations of Black Box Models , 2017, ArXiv.

[26]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001, Statistical Science.

[27]  Zachary Chase Lipton The mythos of model interpretability , 2016, ACM Queue.

[28]  Cynthia Rudin,et al.  Supersparse linear integer models for optimized medical scoring systems , 2015, Machine Learning.

[29]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[30]  C. O’Brien Statistical Learning with Sparsity: The Lasso and Generalizations , 2016 .

[31]  Jonathan Taylor,et al.  Statistical learning and selective inference , 2015, Proceedings of the National Academy of Sciences.