From Predictions to Decisions: Using Lookahead Regularization
arXiv:2006.11638
Abstract
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.
References in corpus (6)
- Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
- Differentiable Convex Optimization Layers
- Accurate Uncertainty Estimation and Decomposition in Ensemble Learning
- Strategic Classification is Causal Modeling in Disguise
- Maximizing Welfare with Incentive-Aware Evaluation Mechanisms
- Extracting Incentives from Black-Box Decisions