Mechanism design for cost optimal PAC learning in the presence of strategic noisy annotators

Garg, Dinesh and Bhattacharya, Sourangshu and Sundararajan, S and Shevade, Shirish (2012) Mechanism design for cost optimal PAC learning in the presence of strategic noisy annotators. In: UAI 2012 : 28th Conference on Uncertainty in Artificial Intelligence, August 15-17, 2012, Catalina Island, USA.

PDF Asso_Unce_Arti_Intel_1_2012.pdf - Published Version Restricted to Registered users only Download (222kB) | Request a copy

Abstract

We consider the problem of Probably Ap-proximate Correct (PAC) learning of a bi-nary classifier from noisy labeled exam-ples acquired from multiple annotators(each characterized by a respective clas-sification 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 Mini-mum Disagreement Algorithm (MDA) on the number of labeled examples to be ob-tained from each annotator. Next, we consider the incomplete information sce-nario, where each annotator is strategic and holds the respective noise rate as a private information. For this scenario, we design a cost optimal procurement auc-tion mechanism along the lines of Myer-son’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.

Item Type:	Conference Paper
Publisher:	Association for Uncertainty in Artificial Intelligence
Additional Information:	Copyright of this article belongs to Association for Uncertainty in Artificial Intelligence.
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	22 Nov 2013 11:37
Last Modified:	22 Nov 2013 11:37
URI:	http://eprints.iisc.ac.in/id/eprint/47816

Actions (login required)

View Item