Search

We investigate the query complexity of the fair allocation of indivisible goods. For two agents with arbitrary monotonic utilities, we design an algorithm that computes an allocation satisfying envy-freeness up to one good (EF1), a relaxation of envy-freeness, using a logarithmic number of queries. We show that the logarithmic query complexity bound also holds for three agents with additive utilities and that a polylogarithmic bound holds for three agents with monotonic utilities. These results suggest that it is possible to fairly allocate goods in practice even when the number of goods is extremely large. By contrast, we prove that computing an allocation satisfying envy-freeness and another of its relaxations, envy-freeness up to any good (EFX), requires a linear number of queries even when there are only two agents with identical additive utilities. [ABSTRACT FROM AUTHOR]

We present the first model of optimal voting under adversarial noise. From this viewpoint, voting rules are seen as error-correcting codes: their goal is to correct errors in the input rankings and recover a ranking that is close to the ground truth. We derive worst-case bounds on the relation between the average accuracy of the input votes, and the accuracy of the output ranking. Empirical results from real data show that our approach produces significantly more accurate rankings than alternative approaches. [ABSTRACT FROM AUTHOR]

Abstract: The strategyproof classification problem deals with a setting where a decision maker must classify a set of input points with binary labels, while minimizing the expected error. The labels of the input points are reported by self-interested agents, who might lie in order to obtain a classifier that more closely matches their own labels, thereby creating a bias in the data; this motivates the design of truthful mechanisms that discourage false reports. In this paper we give strategyproof mechanisms for the classification problem in two restricted settings: (i) there are only two classifiers, and (ii) all agents are interested in a shared set of input points. We show that these plausible assumptions lead to strong positive results. In particular, we demonstrate that variations of a random dictator mechanism, that are truthful, can guarantee approximately optimal outcomes with respect to any family of classifiers. Moreover, these results are tight in the sense that they match the best possible approximation ratio that can be guaranteed by any truthful mechanism. We further show how our mechanisms can be used for learning classifiers from sampled data, and provide PAC-style generalization bounds on their expected error. Interestingly, our results can be applied to problems in the context of various fields beyond classification, including facility location and judgment aggregation. [Copyright &y& Elsevier]

Abstract: In cooperative multiagent systems an alternative that maximizes the social welfare—the sum of utilities—can only be selected if each agent reports its full utility function. This may be infeasible in environments where communication is restricted. Employing a voting rule to choose an alternative greatly reduces the communication burden, but leads to a possible gap between the social welfare of the optimal alternative and the social welfare of the one that is ultimately elected. Procaccia and Rosenschein (2006) have introduced the concept of distortion to quantify this gap. In this paper, we present the notion of embeddings into voting rules: functions that receive an agentʼs utility function and return the agentʼs vote. We establish that very low distortion can be obtained using randomized embeddings, especially when the number of agents is large compared to the number of alternatives. We investigate our ideas in the context of three prominent voting rules with low communication costs: Plurality, Approval, and Veto. Our results arguably provide a compelling reason for employing voting in cooperative multiagent systems. [Copyright &y& Elsevier]

Implementation theory tackles the following problem given a social choice correspondence (SCC), find a decentralized mechanism such that for every constellation of the individuals’ preferences, the set of outcomes in equilibrium is exactly the set of socially optimal alternatives (as specified by the correspondence). In this paper we are concerned with implementation by mediated equilibrium; under such an equilibrium, the players’ strategies can be coordinated in a way that discourages deviation. Our main result is a complete characterization of SCCs that are implementable by mediated strong equilibrium. This characterization, in addition to being strikingly concise, implies that some important SCCs that are not implementable by strong equilibrium are in fact implementable by mediated strong equilibrium. [ABSTRACT FROM AUTHOR]

Abstract: Scoring rules and voting trees are two broad and concisely-representable classes of voting rules; scoring rules award points to alternatives according to their position in the preferences of the voters, while voting trees are iterative procedures that select an alternative based on pairwise comparisons. In this paper, we investigate the PAC-learnability of these classes of rules. We demonstrate that the class of scoring rules, as functions from preferences into alternatives, is efficiently learnable in the PAC model. With respect to voting trees, while in general a learning algorithm would require an exponential number of samples, we show that if the number of leaves is polynomial in the size of the set of alternatives, then a polynomial training set suffices. We apply these results in an emerging theory: automated design of voting rules by learning. [Copyright &y& Elsevier]

Abstract: We investigate the problem of coalitional manipulation in elections, which is known to be hard in a variety of voting rules. We put forward efficient algorithms for the problem in Borda, Maximin and Plurality with Runoff, and analyze their windows of error. Specifically, given an instance on which an algorithm fails, we bound the additional power the manipulators need in order to succeed. We finally discuss the implications of our results with respect to the popular approach of employing computational hardness to preclude manipulation. [Copyright &y& Elsevier]

We demonstrate that winner selection in two prominent proportional representation voting systems is a computationally intractable problem—implying that these systems are impractical when the assembly is large. On a different note, in settings where the size of the assembly is constant, we show that the problem can be solved in polynomial time. [ABSTRACT FROM AUTHOR]

We present two models of how people form beliefs that are based on machine learning theory. We illustrate how these models give insight into observed human phenomena by showing how polarized beliefs can arise even when people are exposed to almost identical sources of information. In our first model, people form beliefs that are deterministic functions that best fit their past data (training sets). In that model, their inability to form probabilistic beliefs can lead people to have opposing views even if their data are drawn from distributions that only slightly disagree. In the second model, people pay a cost that is increasing in the complexity of the function that represents their beliefs. In this second model, even with large training sets drawn from exactly the same distribution, agents can disagree substantially because they simplify the world along different dimensions. We discuss what these models of belief formation suggest for improving people's accuracy and agreement. [ABSTRACT FROM AUTHOR]

We study a mechanism design version of matching computation in graphs that models the game played by hospitals participating in pairwise kidney exchange programs. We present a new randomized matching mechanism for two agents which is truthful in expectation and has an approximation ratio of 3/2 to the maximum cardinality matching. This is an improvement over a recent upper bound of 2 (Ashlagi et al., 2010 [2] ) and, furthermore, our mechanism beats for the first time the lower bound on the approximation ratio of deterministic truthful mechanisms. We complement our positive result with new lower bounds. Among other statements, we prove that the weaker incentive compatibility property of truthfulness in expectation in our mechanism is necessary; universally truthful mechanisms that have an inclusion-maximality property have an approximation ratio of at least 2. [ABSTRACT FROM AUTHOR]

Abstract: Consider the unit circle with distance function measured along the circle. We show that for every selection of points there exists such that . We also discuss a game theoretic interpretation of this result. [ABSTRACT FROM AUTHOR]

Abstract: We initiate the study of incentives in a general machine learning framework. We focus on a game-theoretic regression learning setting where private information is elicited from multiple agents with different, possibly conflicting, views on how to label the points of an input space. This conflict potentially gives rise to untruthfulness on the part of the agents. In the restricted but important case when every agent cares about a single point, and under mild assumptions, we show that agents are motivated to tell the truth. In a more general setting, we study the power and limitations of mechanisms without payments. We finally establish that, in the general setting, the VCG mechanism goes a long way in guaranteeing truthfulness and economic efficiency. [ABSTRACT FROM AUTHOR]

We adopt a utilitarian perspective on social choice, assuming that agents have (possibly latent) utility functions over some space of alternatives. For many reasons one might consider mechanisms, or social choice functions , that only have access to the ordinal rankings of alternatives by the individual agents rather than their utility functions. In this context, one possible objective for a social choice function is the maximization of (expected) social welfare relative to the information contained in these rankings. We study such optimal social choice functions under three different models, and underscore the important role played by scoring functions . In our worst-case model, no assumptions are made about the underlying distribution and we analyze the worst-case distortion —or degree to which the selected alternative does not maximize social welfare—of optimal (randomized) social choice functions. In our average-case model, we derive optimal functions under neutral (or impartial culture) probabilistic models. Finally, a very general learning-theoretic model allows for the computation of optimal social choice functions (i.e., ones that maximize expected social welfare) under arbitrary, sampleable distributions. In the latter case, we provide both algorithms and sample complexity results for the class of scoring functions, and further validate the approach empirically. [ABSTRACT FROM AUTHOR]

As kidney exchange programs are growing, manipulation by hospitals becomes more of an issue. Assuming that hospitals wish to maximize the number of their own patients who receive a kidney, they may have an incentive to withhold some of their incompatible donor–patient pairs and match them internally, thus harming social welfare. We study mechanisms for two-way exchanges that are strategyproof, i.e., make it a dominant strategy for hospitals to report all their incompatible pairs. We establish lower bounds on the welfare loss of strategyproof mechanisms, both deterministic and randomized, and propose a randomized mechanism that guarantees at least half of the maximum social welfare in the worst case. Simulations using realistic distributions for blood types and other parameters suggest that in practice our mechanism performs much closer to optimal. [ABSTRACT FROM AUTHOR]

Abstract: Cake cutting is a common metaphor for the division of a heterogeneous divisible good. There are numerous papers that study the problem of fairly dividing a cake; a small number of them also take into account self-interested agents and consequent strategic issues, but these papers focus on fairness and consider a strikingly weak notion of truthfulness. In this paper we investigate the problem of cutting a cake in a way that is truthful, Pareto-efficient, and fair, where for the first time our notion of dominant strategy truthfulness is the ubiquitous one in social choice and computer science. We design both deterministic and randomized cake cutting mechanisms that are truthful and fair under different assumptions with respect to the valuation functions of the agents. [Copyright &y& Elsevier]

Abstract: The voting rules proposed by Dodgson and Young are both designed to find an alternative closest to being a Condorcet winner, according to two different notions of proximity; the score of a given alternative is known to be hard to compute under either rule. In this paper, we put forward two algorithms for approximating the Dodgson score: a combinatorial, greedy algorithm and an LP-based algorithm, both of which yield an approximation ratio of , where m is the number of alternatives and is the st harmonic number. We also prove that our algorithms are optimal within a factor of 2, unless problems in have quasi-polynomial-time algorithms. Despite the intuitive appeal of the greedy algorithm, we argue that the LP-based algorithm has an advantage from a social choice point of view. Further, we demonstrate that computing any reasonable approximation of the ranking produced by Dodgsonʼs rule is -hard. This result provides a complexity-theoretic explanation of sharp discrepancies that have been observed in the social choice theory literature when comparing Dodgson elections with simpler voting rules. Finally, we show that the problem of calculating the Young score is -hard to approximate by any factor. This leads to an inapproximability result for the Young ranking. [Copyright &y& Elsevier]