Michael J. Kearns

Learn More
This article applies an earlier analysis of interdependent security issues to a general class of problems involving discrete interdependent exposure to terrorist risks. Any agent’s incentive to adopt risk-reducing measures depends on the actions of others because of the negative externalities created by not investing in protection. Using airline security as(More)
This paper develops a framework for analyzing individuals’ choices in the presence of endogenous social networks and implements it with data on teen smoking decisions and friendship networks. By allowing actions and friendships to be jointly chosen, the framework extends the literature on social interactions, which either models choices, taking the social(More)
In this chapter we examine the representational and algorithmic aspects of a class of graph-theoretic models for multiplayer games. Known broadly as graphical games, these models specify restrictions on the direct payoff influences among the player population. In addition to a number of nice computational properties, these models have close connections to(More)
Genes interact in networks to orchestrate cellular processes. Analysis of these networks provides insights into gene interactions and functions. Here, we took advantage of normal variation in human gene expression to infer gene networks, which we constructed using correlations in expression levels of more than 8.5 million gene pairs in immortalized B cells(More)
This paper extends our earlier analysis of interdependent security issues to a general class of problems involving discrete interdependent risks with heterogeneous agents. There is a threat of an event that can only happen once, and the risk depends on actions taken by others. Any agent’s incentive to invest in managing the risk depends on the actions of(More)
Effective use of subjective judgment is essential in all fields of knowledge. We present a method for finding truth when the subjective judgments of multiple respondents are the only evidence available, and majority opinion may be wrong. Respondents are scored for their own judgments and for their metaknowledge of others’ judgments. In a probabilistic model(More)
In this paper, we study the extension of Valiant's learning model [32] in which the positive or negative classi cation label provided with each random example may be corrupted by random noise. This extension was rst examined in the learning theory literature by Angluin and Laird [1], who formalized the simplest type of white label noise and then sought(More)
Cells respond to variable environments by changing gene expression and gene interactions. To study how human cells response to stress, we analyzed the expression of >5000 genes in cultured B cells from nearly 100 normal individuals following endoplasmic reticulum stress and exposure to ionizing radiation. We identified thousands of genes that are induced or(More)
We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approximate an unknown target function arbitrarily well. Our motivation includes the question of how to make optimal use of multiple independent runs of a mediocre learning algorithm, as(More)