Counterfactual Reasoning and Learning Systems

Abstract

This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Such predictions allow both humans and algorithms to select changes that improve both the short-term and long-term performance of such systems. This work is illustrated by experiments carried out on the ad placement system associated with the Bing search engine.

revised version

References in corpus (4)

• Doubly Robust Policy Evaluation and Learning
• Contextual Bandits with Similarity Information
• Learning from Logged Implicit Exploration Data
• From Machine Learning to Machine Reasoning

Cited by in corpus (7)

• Residual Unfairness in Fair Machine Learning from Prejudiced Data
• Adapting Neural Networks for the Estimation of Treatment Effects
• Improving offline evaluation of contextual bandit algorithms via bootstrapping techniques
• Comparative Benchmarking of Causal Discovery Techniques
• Task Selection Policies for Multitask Learning
• Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion
• Ranking metrics on non-shuffled traffic