AI & ML
Designing Algorithmic Recommendations to Achieve Human-AI Complementarity
arXiv stat.ML0 views
arXiv:2405.01484v3 Announce Type: replace-cross Abstract: Algorithms frequently assist, rather than replace, human decision-makers. However, the design and analysis of algorithms often focus on predicting outcomes and do not explicitly model their effect on human decisions. This discrepancy between the design and role of algorithmic assistants becomes particularly concerning in light of empirical evidence that suggests that algorithmic assistants again and again fail to improve human decisions. In this article, we formalize the design of recommendation algorithms that assist human decision-makers without making restrictive ex-ante assumptions about how recommendations affect decisions. We formulate an algorithmic-design problem that leverages the potential-outcomes framework from causal inference to model the effect of recommendations on a human decision-maker's binary treatment choice. Within this model, we make a connection between algorithmic recommendations and instrumental variables. Leveraging this connection, we introduce a monotonicity assumption that leads to an intuitive classification of human responses to the algorithm. Under this assumption, we can express the human's response to algorithmic recommendations in terms of their compliance with the algorithm and the active decision they would take if the algorithm sends no recommendation. We showcase the utility of our framework using an online experiment that simulates a hiring task. We argue that our approach can make sense of the relative performance of different recommendation algorithms in the experiment and can help design solutions that realize human-AI complementarity. Finally, we leverage our approach to derive maximin-optimal recommendation algorithms that can be implemented with machine learning using limited training data.
Source:https://arxiv.org/abs/2405.01484PreviousActive Learning For Contextual Linear Optimization: A Margin-Based ApproachNextAlmost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise
Related posts
How we find viral moments in a 6-hour stream in 4 minutes
0dev.to
One red light, four stalls
0dev.to
Testing Political Alignment in Chinese AI Models: What Developers Need to Know
0dev.to
LLM Inference Optimization Interview Questions and Answers
0dev.to
How to Close a Deal That Keeps Stalling: A Mutual Action Plan Template and Closing Techniques for Founder-Led Sales
0dev.to

Roast My Dev Desktop: Zero Minimalism, Maximum Chaos
0dev.to