The Optimal Sample Complexity of Linear Contracts
A new paper published on arXiv details an algorithm for learning optimal linear contracts from data. The Empirical Utility Maximization (EUM) algorithm can achieve an \(\\varepsilon\)-approximation of the best possible linear contract with high probability, using a sample complexity of \(O(\ln(1/\delta) / \varepsilon^2)\). This sample complexity is proven to be optimal, matching existing lower bounds and establishing uniform convergence guarantees. AI