# Approximate Optimality of Linear Contracts Under Uncertainty

arXiv: https://arxiv.org/abs/2211.06850 · HTML: https://mlsanity.com/paper/2211.06850/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2022.

## Built on by (most cited first, 7 of 7)

- [Contracting with a Learning Agent](https://mlsanity.com/paper/2401.16198/) (2024)
- [Deep Contract Design via Discontinuous Networks](https://mlsanity.com/paper/2307.02318/) (2023)
- [Delegating Data Collection in Decentralized Machine Learning](https://mlsanity.com/paper/2309.01837/) (2023)
- [Are Bounded Contracts Learnable and Approximately Optimal?](https://mlsanity.com/paper/2402.14486/) (2024)
- [Learning Optimal Contracts: How to Exploit Small Action Spaces](https://mlsanity.com/paper/2309.09801/) (2023)
- [The Backfiring Effect of Weak AI Safety Regulation](https://mlsanity.com/paper/2503.20848/) (2025)
- [Operationalizing Counterfactual Metrics: Incentives, Ranking, and Information Asymmetry](https://mlsanity.com/paper/2305.14595/) (2023)

## Abstract (arXiv)

We consider a hidden-action principal-agent model, in which actions require different amounts of effort, and the agent privately knows his ability that determines his cost of effort. We show that linear contracts admit approximation guarantees that improve with a natural metric that captures the degree of uncertainty in the contracting setting. We thus show that linear contracts are near-optimal whenever there is enough uncertainty. In contrast, other simple contract formats such as debt contracts may suffer from a loss linear in the number of possible actions, even when there is sufficient uncertainty.