From Predictions to Decisions: Using Lookahead Regularization

Machine learning is a powerful tool for predicting human-related outcomes, from credit scores to heart attack risks. But when deployed, learned models also affect how users act in order to improve outcomes, whether predicted or real. The standard approach to learning is agnostic to induced user actions and provides no guarantees as to the effect of actions. We provide a framework for learning predictors that are both accurate and promote good actions. For this, we introduce look-ahead regularization which, by anticipating user actions, encourages predictive models to also induce actions that improve outcomes. This regularization carefully tailors the uncertainty estimates governing confidence in this improvement to the distribution of model-induced actions. We report the results of experiments on real and synthetic data that show the effectiveness of this approach.

[1]  John C. Duchi,et al.  Certifying Some Distributional Robustness with Principled Adversarial Training , 2017, ICLR.

[2]  Naeem Siddiqi,et al.  Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring , 2005 .

[3]  Karsten M. Borgwardt,et al.  Covariate Shift by Kernel Mean Matching , 2009, NIPS 2009.

[4]  Tommi S. Jaakkola,et al.  Learning Optimal Interventions , 2016, AISTATS.

[5]  Jonas Peters,et al.  Causal inference by using invariant prediction: identification and confidence intervals , 2015, 1501.01332.

[6]  Neil D. Lawrence,et al.  Dataset Shift in Machine Learning , 2009 .

[7]  A. Baranchuk,et al.  Wine and Cardiovascular Health: A Comprehensive Review , 2017, Circulation.

[8]  Ryan P. Adams,et al.  Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks , 2015, ICML.

[9]  Gunnar Rätsch,et al.  An Empirical Analysis of Domain Adaptation Algorithms for Genomic Sequence Analysis , 2008, NIPS.

[10]  Stephen P. Boyd,et al.  Differentiable Convex Optimization Layers , 2019, NeurIPS.

[11]  Steffen Bickel,et al.  Discriminative Learning Under Covariate Shift , 2009, J. Mach. Learn. Res..

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

[13]  Adam Tauman Kalai,et al.  The disparate equilibria of algorithmic decision making when individuals invest rationally , 2019, FAT*.

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

[15]  J. Pearl.  Causal inference in statistics: An overview , 2009 .

[16]  William S. Moses,et al.  Extracting Incentives from Black-Box Decisions , 2019, ArXiv.

[17]  Klaus-Dieter Thoben,et al.  Machine learning in manufacturing: advantages, challenges, and applications , 2016 .

[18]  Jeremiah Liu,et al.  Accurate Uncertainty Estimation and Decomposition in Ensemble Learning , 2019, NeurIPS.

[19]  Nicolai Meinshausen,et al.  CAUSALITY FROM A DISTRIBUTIONAL ROBUSTNESS POINT OF VIEW , 2018, 2018 IEEE Data Science Workshop (DSW).

[20]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[21]  N. Meinshausen,et al.  Anchor regression: Heterogeneous data meet causality , 2018, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[22]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

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

[24]  Jun S. Liu,et al.  Sequential Imputations and Bayesian Missing Data Problems , 1994 .

[25]  Naomi S. Altman,et al.  Quantile regression , 2019, Nature Methods.

[26]  Nicole Immorlica,et al.  Maximizing Welfare with Incentive-Aware Evaluation Mechanisms , 2020, IJCAI.

[27]  Jon M. Kleinberg,et al.  How Do Classifiers Induce Agents to Invest Effort Strategically? , 2018, EC.

[28]  Bernhard Schölkopf,et al.  Invariant Models for Causal Transfer Learning , 2015, J. Mach. Learn. Res..

[29]  Benjamin Edelman,et al.  Learning From Strategic Agents: Accuracy, Improvement, and Causality , 2020, ICML 2020.

[30]  Brian Axelrod,et al.  Causal Strategic Linear Regression , 2020, ICML.

[31]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[32]  Zhiwei Steven Wu,et al.  Gaming Helps! Learning from Strategic Interactions in Natural Dynamics , 2021, AISTATS.

[33]  Bernhard Schölkopf,et al.  Optimal Decision Making Under Strategic Behavior , 2019, ArXiv.

[34]  Aaron Roth,et al.  Strategic Classification from Revealed Preferences , 2017, EC.

[35]  Tobias Scheffer,et al.  Stackelberg games for adversarial prediction problems , 2011, KDD.

[36]  A. Sahebkar,et al.  Lack of efficacy of resveratrol on C-reactive protein and selected cardiovascular risk factors--Results from a systematic review and meta-analysis of randomized controlled trials. , 2015, International journal of cardiology.

[37]  Nicole Immorlica,et al.  The Disparate Effects of Strategic Manipulation , 2018, FAT.

[38]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[39]  Anca D. Dragan,et al.  The Social Cost of Strategic Classification , 2018, FAT.

[40]  David Lopez-Paz,et al.  Single-Model Uncertainties for Deep Learning , 2018, NeurIPS.

[41]  Motoaki Kawanabe,et al.  Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation , 2007, NIPS.

[42]  Alison Callahan,et al.  Machine Learning in Healthcare , 2017 .

[43]  Moritz Hardt,et al.  Strategic Classification is Causal Modeling in Disguise , 2019, ICML.

[44]  H. Shimodaira,et al.  Improving predictive inference under covariate shift by weighting the log-likelihood function , 2000 .

[45]  Moritz Hardt,et al.  Strategic Adaptation to Classifiers: A Causal Perspective , 2019, ArXiv.

[46]  Christos H. Papadimitriou,et al.  Strategic Classification , 2015, ITCS.

[47]  Takafumi Kanamori,et al.  A Least-squares Approach to Direct Importance Estimation , 2009, J. Mach. Learn. Res..

[48]  Sebastian Nowozin,et al.  Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift , 2019, NeurIPS.

[49]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .