Delegated Classification

Abstract: What happens when machine learning is outsourced to profit-maximizing agents?

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.

Bio: Eden Saig is a computer science PhD student at the Technion (3rd year), advised by Nir Rosenfeld. His research aims to develop socially favorable learning algorithms for behavioral environments with dynamics and incentives. Eden is supported by the Israeli Council for Higher Education (CHE) scholarship for excellent doctoral students in Data Science. Before starting his PhD, Eden was a research scientist at the Facebook Core Data Science group. He holds a BSc in Computer Science, BSc in Physics, and an MSc in Computer Science, all from the Technion.