Kearns, Michael J
Email Address
ORCID
Disciplines
Search Results
Now showing 1 - 10 of 16
Publication Colonel Blotto on Facebook: The Effect of Social Relations on Strategic Interaction(2012-06-01) Kohli, Pushmeet; Bachrach, Yoram; Stillwell, David; Kearns, Michael J; Herbrich, Ralf; Graepel, ThoreWe study how social relations between people affect the way they play the famous resource allocation game called Colonel Blotto. We report the deployment of a Facebook application called “Project Waterloo” which allows users to invite both friends and strangers to play Colonel Blotto against them. Most previous empirical studies of Blotto have been performed in a laboratory environment and have typically employed monetary incentives to attract human subjects to play games. In contrast, our framework relies on reputation and entertainment incentives to attract players. Deploying the game on a social network allows us to capture the social relations between players and analyze their impact on the used strategies. Following [1] we examine player strategies and contrast them with game theoretic predictions. We then investigate how strategies are affected by social relations. Our analysis reveals that knowledge of the opponent affects the strategies chosen by players and how well they perform in the game. We show that players with few Facebook friends tend to play more games and have a higher probability of winning, that players responding to a challenge in the game have a higher probability of winning than those initiating the game, and that the initiators of a game have a higher probability of defeating their friends than strangers.Publication Local Algorithms for Finding Interesting Individuals in Large Networks(2010-01-01) Brautbar, Michael; Kearns, Michael JWe initiate the study of local, sublinear time algorithms for finding vertices with extreme topological properties — such as high degree or clustering coefficient — in large social or other networks. We introduce a new model, called the Jump and Crawl model, in which algorithms are permitted only two graph operations. The Jump operation returns a randomly chosen vertex, and is meant to model the ability to discover “new” vertices via keyword search in the Web, shared hobbies or interests in social networks such as Facebook, and other mechanisms that may return vertices that are distant from all those currently known. The Crawl operation permits an algorithm to explore the neighbors of any currently known vertex, and has clear analogous in many modern networks. We give both upper and lower bounds in the Jump and Crawl model for the problems of finding vertices of high degree and high clustering coefficient. We consider both arbitrary graphs, and specializations in which some common assumptions are made on the global topology (such as power law degree distributions or generation via preferential attachment). We also examine local algorithms for some related vertex or graph properties, and discuss areas for future investigation.Publication Learning from Multiple Sources(2008-06-01) Crammer, Koby; Kearns, Michael; Wortman, JenniferWe consider the problem of learning accurate models from multiple sources of "nearby" data. Given distinct samples from multiple data sources and estimates of the dissimilarities between these sources, we provide a general theory of which samples should be used to learn models for each source. This theory is applicable in a broad decision-theoretic learning framework, and yields general results for classification and regression. A key component of our approach is the development of approximate triangle inequalities for expected loss, which may be of independent interest. We discuss the related problem of learning parameters of a distribution from multiple data sources. Finally, we illustrate our theory through a series of synthetic simulations.Publication Learning and Predicting Dynamic Behavior with Graphical Multiagent Models(2012-06-01) Duong, Quang; Wellman, Michael P.; Singh, Satinder; Kearns, Michael JFactored models of multiagent systems address the complexity of joint behavior by exploiting locality in agent interactions. History-dependent graphical multiagent models (hGMMs) further capture dynamics by conditioning behavior on history. The challenges of modeling real human behavior motivated us to extend the hGMM representation by distinguishing two types of agent interactions. This distinction opens the opportunity for learning dependence networks that are different from given graphical structures representing observed agent interactions. We propose a greedy algorithm for learning hGMMs from time-series data, inducing both graphical structure and parameters. Our empirical study employs human-subject experiment data for a dynamic consensus scenario, where agents on a network attempt to reach a unanimous vote. We show that the learned hGMMs directly expressing joint behavior outperform alternatives in predicting dynamic human voting behavior, and end-game vote results. Analysis of learned graphical structures reveals patterns of action dependence not directly reflected in the original experiment networks.Publication Behavioral Conflict and Fairness in Social Networks(2011-12-01) Judd, Stephen; Kearns, Michael J; Vorobeychik, YevgeniyWe report on a series of behavioral experiments in social networks in which human subjects continuously choose to play either a dominant role (called a King) or a submissive one (called a Pawn). Kings receive a higher payoff rate, but only if all their network neighbors are Pawns, and thus the maximum social welfare states correspond to maximum independent sets. We document that fairness is of vital importance in driving interactions between players. First, we find that payoff disparities between network neighbors gives rise to conflict, and the specifics depend on the network topology. However, allowing Kings to offer "tips" or side payments to their neighbors substantially reduces conflict, and consistently increases social welfare. Finally, we observe that tip reductions lead to increased conflict. We describe these and a broad set of related findings.Publication Competitive Contagion in Networks(2012-05-01) Goyal, Sanjeev; Kearns, Michael JWe develop a game-theoretic framework for the study of competition between firms who have budgets to "seed" the initial adoption of their products by consumers located in a social network. The payoffs to the firms are the eventual number of adoptions of their product through a competitive stochastic diffusion process in the network. This framework yields a rich class of competitive strategies, which depend in subtle ways on the stochastic dynamics of adoption, the relative budgets of the players, and the underlying structure of the social network. We identify a general property of the adoption dynamics—namely, decreasing returns to local adoption—for which the inefficiency of resource use at equilibrium (the Price of Anarchy) is uniformly bounded above, across all networks. We also show that if this property is violated the Price of Anarchy can be unbounded, thus yielding sharp threshold behavior for a broad class of dynamics. We also introduce a new notion, the Budget Multiplier, that measures the extent that imbalances in player budgets can be amplified at equilibrium. We again identify a general property of the adoption dynamics—namely, proportional local adoption between competitors—for which the (pure strategy) Budget Multiplier is uniformly bounded above, across all networks. We show that a violation of this property can lead to unbounded Budget Multiplier, again yielding sharp threshold behavior for a broad class of dynamics.Publication Behavioral Experiments on a Network Formation Game(2012-06-01) Kearns, Michael J; Judd, Stephen; Vorobeychik, YevgeniyWe report on an extensive series of behavioral experiments in which 36 human subjects collectively build a communication network over which they must solve a competitive coordination task for monetary compensation. There is a cost for creating network links, thus creating a tension between link expenditures and collective and individual incentives. Our most striking finding is the poor performance of the subjects, especially compared to our long series of prior experiments. We demonstrate that the subjects built difficult networks for the coordination task, and compare the structural properties of the built networks to standard generative models of social networks. We also provide extensive analysis of the individual and collective behavior of the subjects, including free riding and factors influencing edge purchasing decisions.Publication Graphical Models for Bandit Problems(2011-07-01) Amin, Kareem; Kearns, Michael J; Syed, UmarWe introduce a rich class of graphical models for multi-armed bandit problems that permit both the state or context space and the action space to be very large, yet succinctly specify the payoffs for any context-action pair. Our main result is an algorithm for such models whose regret is bounded by the number of parameters and whose running time depends only on the treewidth of the graph substructure induced by the action space.Publication The Penn-Lehman Automated Trading Project(2003-11-01) Kearns, Michael J; Ortiz, LuisThe Penn-Lehman Automated Trading Project is a broad investigation of algorithms and strategies for automated trading in financial markets. The PLAT Project’s centerpiece is the Penn Exchange Simulator (PXS), a software simulator for automated stock trading that merges automated client orders for shares with real-world, real-time order data. PXS automatically computes client profits and losses, volumes traded, simulator and external prices, and other quantities of interest. To test the effectiveness of PXS and of various trading strategies, we’ve held three formal competitions between automated clients.Publication Empirical Limitations on High Frequency Trading Profitability(2010-01-01) Kearns, Michael J; Kulesza, Alex; Nevmyvaka, YuriyAddressing the ongoing examination of high-frequency trading practices in financial markets, we report the results of an extensive empirical study estimating the maximum possible profitability of the most aggressive such practices, and arrive at figures that are surprisingly modest. By “aggressive” we mean any trading strategy exclusively employing market orders and relatively short holding periods. Our findings highlight the tension between execution costs and trading horizon confronted by high-frequency traders, and provide a controlled and large-scale empirical perspective on the high-frequency debate that has heretofore been absent. Our study employs a number of novel empirical methods, including the simulation of an “omniscient” high-frequency trader who can see the future and act accordingly.