Delegated Classification
This addresses incentive misalignment in outsourced ML for stakeholders like businesses or policymakers, but it is incremental as it adapts existing economic theory to a new context.
The paper tackles the problem of conflicts of interest when outsourcing machine learning to rational agents by proposing a theoretical framework for incentive-aware delegation, showing that budget-optimal contracts take a simple threshold form and can be constructed using small-scale data.
When machine learning is outsourced to a rational agent, conflicts of interest might arise and severely impact predictive performance. In this work, we propose a theoretical framework for incentive-aware delegation of machine learning tasks. We model delegation as a principal-agent game, in which accurate learning can be incentivized by the principal using performance-based contracts. Adapting the economic theory of contract design to this setting, we define budget-optimal contracts and prove they take a simple threshold form under reasonable assumptions. In the binary-action case, the optimality of such contracts is shown to be equivalent to the classic Neyman-Pearson lemma, establishing a formal connection between contract design and statistical hypothesis testing. Empirically, we demonstrate that budget-optimal contracts can be constructed using small-scale data, leveraging recent advances in the study of learning curves and scaling laws. Performance and economic outcomes are evaluated using synthetic and real-world classification tasks.