Searcharxiv⌕ Search

arXiv subjects

Michael Kearns

Publications and source records attributed to Michael Kearns.

70 records · Page 4Linked to original sources
arXiv2015

Graphical Models for Game Theory

In this work, we introduce graphical modelsfor multi-player game theory, and give powerful algorithms for computing their Nash equilibria in certain cases. An n-player game is given by an undirected graph on n nodes and a set of n local matrices. The interpretation is that the payoff to player i is determined entirely by the actions of player i and his neighbors in the graph, and thus the payoff matrix to player i is indexed only by these players. We thus view the global n-player game as being composed of interacting local games, each involving many fewer players. Each player's action may have global impact, but it occurs through the propagation of local influences.Our main technical result is an efficient algorithm for computing Nash equilibria when the underlying graph is a tree (or can be turned into a tree with few node mergings). The algorithm runs in time polynomial in the size of the representation (the graph and theassociated local game matrices), and comes in two related but distinct flavors. The first version involves an approximation step, and computes a representation of all approximate Nash equilibria (of which there may be an exponential number in general). The second version allows the exact computation of Nash equilibria at the expense of weakened complexity bounds. The algorithm requires only local message-passing between nodes (and thus can be implemented by the players themselves in a distributed manner). Despite an analogy to inference in Bayes nets that we develop, the analysis of our algorithm is more involved than that for the polytree algorithm in, owing partially to the fact that we must either compute, or select from, an exponential number of potential solutions. We discuss a number of extensions, such as the computation of equilibria with desirable global properties (e.g. maximizing global return), and directions for further research.

cs.GT↗
arXiv2015

Privacy and Truthful Equilibrium Selection for Aggregative Games

We study a very general class of games --- multi-dimensional aggregative games --- which in particular generalize both anonymous games and weighted congestion games. For any such game that is also large, we solve the equilibrium selection problem in a strong sense. In particular, we give an efficient weak mediator: a mechanism which has only the power to listen to reported types and provide non-binding suggested actions, such that (a) it is an asymptotic Nash equilibrium for every player to truthfully report their type to the mediator, and then follow its suggested action; and (b) that when players do so, they end up coordinating on a particular asymptotic pure strategy Nash equilibrium of the induced complete information game. In fact, truthful reporting is an ex-post Nash equilibrium of the mediated game, so our solution applies even in settings of incomplete information, and even when player types are arbitrary or worst-case (i.e. not drawn from a common prior). We achieve this by giving an efficient differentially private algorithm for computing a Nash equilibrium in such games. The rates of convergence to equilibrium in all of our results are inverse polynomial in the number of players $n$. We also apply our main results to a multi-dimensional market game. Our results can be viewed as giving, for a rich class of games, a more robust version of the Revelation Principle, in that we work with weaker informational assumptions (no common prior), yet provide a stronger solution concept (ex-post Nash versus Bayes Nash equilibrium). In comparison to previous work, our main conceptual contribution is showing that weak mediators are a game theoretic object that exist in a wide variety of games -- previously, they were only known to exist in traffic routing games.

cs.DS↗
arXiv2014

Online Learning and Profit Maximization from Revealed Preferences

We consider the problem of learning from revealed preferences in an online setting. In our framework, each period a consumer buys an optimal bundle of goods from a merchant according to her (linear) utility function and current prices, subject to a budget constraint. The merchant observes only the purchased goods, and seeks to adapt prices to optimize his profits. We give an efficient algorithm for the merchant's problem that consists of a learning phase in which the consumer's utility function is (perhaps partially) inferred, followed by a price optimization step. We also consider an alternative online learning algorithm for the setting where prices are set exogenously, but the merchant would still like to predict the bundle that will be bought by the consumer for purposes of inventory or supply chain management. In contrast with most prior work on the revealed preferences problem, we demonstrate that by making stronger assumptions on the form of utility functions, efficient algorithms for both learning and profit maximization are possible, even in adaptive, online settings.

cs.DS↗
arXiv2014

A Computational Study of Feasible Repackings in the FCC Incentive Auctions

We report the results of a computational study of repacking in the FCC Incentive Auctions. Our interest lies in the structure and constraints of the solution space of feasible repackings. Our analyses are "mechanism-free", in the sense that they identify constraints that must hold regardless of the reverse auction mechanism chosen or the prices offered for broadcaster clearing. We examine topics such as the amount of spectrum that can be cleared nationwide, the geographic distribution of broadcaster clearings required to reach a clearing target, and the likelihood of reaching clearing targets under various models for broadcaster participation. Our study uses FCC interference data and a satisfiability-checking approach, and elucidates both the unavoidable mathematical constraints on solutions imposed by interference, as well as additional constraints imposed by assumptions on the participation decisions of broadcasters.

cs.GT↗
arXiv2013

An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering

Assignment methods are at the heart of many algorithms for unsupervised learning and clustering - in particular, the well-known K-means and Expectation-Maximization (EM) algorithms. In this work, we study several different methods of assignment, including the "hard" assignments used by K-means and the ?soft' assignments used by EM. While it is known that K-means minimizes the distortion on the data and EM maximizes the likelihood, little is known about the systematic differences of behavior between the two algorithms. Here we shed light on these differences via an information-theoretic analysis. The cornerstone of our results is a simple decomposition of the expected distortion, showing that K-means (and its extension for inferring general parametric densities from unlabeled sample data) must implicitly manage a trade-off between how similar the data assigned to each cluster are, and how the data are balanced among the clusters. How well the data are balanced is measured by the entropy of the partition defined by the hard assignments. In addition to letting us predict and verify systematic differences between K-means and EM on specific examples, the decomposition allows us to give a rather general argument showing that K ?means will consistently find densities with less "overlap" than EM. We also study a third natural assignment method that we call posterior assignment, that is close in spirit to the soft assignments of EM, but leads to a surprisingly different algorithm.

cs.LG↗
arXiv2013

Exact Inference of Hidden Structure from Sample Data in Noisy-OR Networks

In the literature on graphical models, there has been increased attention paid to the problems of learning hidden structure (see Heckerman [H96] for survey) and causal mechanisms from sample data [H96, P88, S93, P95, F98]. In most settings we should expect the former to be difficult, and the latter potentially impossible without experimental intervention. In this work, we examine some restricted settings in which perfectly reconstruct the hidden structure solely on the basis of observed sample data.

cs.AI↗
arXiv2013

Large Deviation Methods for Approximate Probabilistic Inference

We study two-layer belief networks of binary random variables in which the conditional probabilities Pr[childlparents] depend monotonically on weighted sums of the parents. In large networks where exact probabilistic inference is intractable, we show how to compute upper and lower bounds on many probabilities of interest. In particular, using methods from large deviation theory, we derive rigorous bounds on marginal probabilities such as Pr[children] and prove rates of convergence for the accuracy of our bounds as a function of network size. Our results apply to networks with generic transfer function parameterizations of the conditional probability tables, such as sigmoid and noisy-OR. They also explicitly illustrate the types of averaging behavior that can simplify the problem of inference in large networks.

cs.LG↗
arXiv2013

Fast Planning in Stochastic Games

Stochastic games generalize Markov decision processes (MDPs) to a multiagent setting by allowing the state transitions to depend jointly on all player actions, and having rewards determined by multiplayer matrix games at each state. We consider the problem of computing Nash equilibria in stochastic games, the analogue of planning in MDPs. We begin by providing a generalization of finite-horizon value iteration that computes a Nash strategy for each player in generalsum stochastic games. The algorithm takes an arbitrary Nash selection function as input, which allows the translation of local choices between multiple Nash equilibria into the selection of a single global Nash equilibrium. Our main technical result is an algorithm for computing near-Nash equilibria in large or infinite state spaces. This algorithm builds on our finite-horizon value iteration algorithm, and adapts the sparse sampling methods of Kearns, Mansour and Ng (1999) to stochastic games. We conclude by descrbing a counterexample showing that infinite-horizon discounted value iteration, which was shown by shaplely to converge in the zero-sum case (a result we give extend slightly here), does not converge in the general-sum case.

cs.GT↗
arXiv2013

Nash Convergence of Gradient Dynamics in Iterated General-Sum Games

Multi-agent games are becoming an increasing prevalent formalism for the study of electronic commerce and auctions. The speed at which transactions can take place and the growing complexity of electronic marketplaces makes the study of computationally simple agents an appealing direction. In this work, we analyze the behavior of agents that incrementally adapt their strategy through gradient ascent on expected payoff, in the simple setting of two-player, two-action, iterated general-sum games, and present a surprising result. We show that either the agents will converge to Nash equilibrium, or if the strategies themselves do not converge, then their average payoffs will nevertheless converge to the payoffs of a Nash equilibrium.

cs.GT↗
arXiv2012

Efficient Nash Computation in Large Population Games with Bounded Influence

We introduce a general representation of large-population games in which each player s influence ON the others IS centralized AND limited, but may otherwise be arbitrary.This representation significantly generalizes the class known AS congestion games IN a natural way.Our main results are provably correct AND efficient algorithms FOR computing AND learning approximate Nash equilibria IN this general framework.

cs.GT↗
arXiv2012

Budget Optimization for Sponsored Search: Censored Learning in MDPs

We consider the budget optimization problem faced by an advertiser participating in repeated sponsored search auctions, seeking to maximize the number of clicks attained under that budget. We cast the budget optimization problem as a Markov Decision Process (MDP) with censored observations, and propose a learning algorithm based on the wellknown Kaplan-Meier or product-limit estimator. We validate the performance of this algorithm by comparing it to several others on a large set of search auction data from Microsoft adCenter, demonstrating fast convergence to optimal performance.

cs.GT↗
arXiv2012

Censored Exploration and the Dark Pool Problem

We introduce and analyze a natural algorithm for multi-venue exploration from censored data, which is motivated by the Dark Pool Problem of modern quantitative finance. We prove that our algorithm converges in polynomial time to a near-optimal allocation policy; prior results for similar problems in stochastic inventory control guaranteed only asymptotic convergence and examined variants in which each venue could be treated independently. Our analysis bears a strong resemblance to that of efficient exploration/ exploitation schemes in the reinforcement learning literature. We describe an extensive experimental evaluation of our algorithm on the Dark Pool Problem using real trading data.

cs.LG↗
arXiv2012

Competitive Contagion in Networks

We 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.

cs.GT↗
arXiv2012

Graphical Models for Bandit Problems

We 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.

cs.LG↗
arXiv2010

Empirical Limitations on High Frequency Trading Profitability

Addressing 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.

q-fin.TR↗