Mechanism Design for Cost Optimal PAC Learning in the Presence of Strategic Noisy Annotators
Dinesh Garg, Sourangshu Bhattacharya, S. Sundararajan, Shirish Shevade
We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all the annotators. For this scenario, we derive sample complexity bound for the Minimum Disagreement Algorithm (MDA) on the number of labeled examples to be obtained from each annotator. Next, we consider the incomplete information scenario, where each annotator is strategic and holds the respective noise rate as a private information. For this scenario, we design a cost optimal procurement auction mechanism along the lines of Myerson's optimal auction design framework in a non-trivial manner. This mechanism satisfies incentive compatibility property, thereby facilitating the learner to elicit true noise rates of all the annotators.
PDF Link: /papers/12/p275-garg.pdf
AUTHOR = "Dinesh Garg
and Sourangshu Bhattacharya and S. Sundararajan and Shirish Shevade",
TITLE = "Mechanism Design for Cost Optimal PAC Learning in the Presence of Strategic Noisy Annotators",
BOOKTITLE = "Proceedings of the Twenty-Eighth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-12)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2012",
PAGES = "275--285"