A1566
Title: Algorithms and incentives in machine learning
Authors: Haifeng Xu - University of Chicago (United States) [presenting]
Abstract: A generic question in statistics is to design approaches that take data as input and output estimation of certain parameters or prediction of some quantities. The standard paradigm often assumes these data are objectively generated from distributions without being affected by any human factors. However, this paradigm ceases to be true when the predictions or estimated parameters will, in turn, affect the data providers' welfare. In such situations, data providers have incentives to alter the data for their own benefit. Thus, the design of any statistical methods must account for potential data manipulations due to data providers' incentives. A general "incentive-aware'' framework is introduced for designing prediction methods. This design paradigm is illustrated with two examples: (1) a very recent and timely application of eliciting authors' truthful private information for improving the peer review systems for today's massive scale machine learning conferences; (2) a very classic problem of PAC-learning classifiers but with strategic providers of data features. In both problems, the presence of incentives is illustrated to fundamentally change the problem's statistical efficiency and how algorithms can help to overcome some statistical barriers.
