Federated learning is a distributed learning paradigm where multiple agents, each only with access to local data, jointly learn a global model. There has recently been an explosion of research aiming not only to improve the accuracy rates of federated learning, but also provide certain guarantees around social good properties such as total error. One branch of this research has taken a game-theoretic

Budget-management systems are one of the key components of modern auction markets. Internet advertising platforms typically offer advertisers the possibility to pace the rate at which their budget is depleted, through budget-pacing mechanisms. We focus on multiplicative pacing mechanisms in an online setting in which a bidder is repeatedly confronted with a series of advertising opportunities. After

Two-player, constant-sum games are well studied in the literature, but there has been limited progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO), an algorithm for training agents in n-player, general-sum extensive form games, which provably converges to an equilibrium. We further suggest correlated equilibria (CE) as promising meta-solvers, and propose a novel

With the development of the 5G and Internet of Things, amounts of wireless devices need to share the limited spectrum resources. Dynamic spectrum access (DSA) is a promising paradigm to remedy the problem of inefficient spectrum utilization brought upon by the historical command-and-control approach to spectrum allocation. In this paper, we investigate the distributed DSA problem for multi-user in

The recent COVID-19 pandemic has led to an increasing interest in the modeling and analysis of infectious diseases. The pandemic has made a significant impact on the way we behave and interact in our daily life. The past year has witnessed a strong interplay between human behaviors and epidemic spreading. In this paper, we propose an evolutionary game-theoretic framework to study the coupled evolutions

Recent work in iterative voting has defined the difference in social welfare between the truthful winner and worst-case equilibrium winner, due to repeated strategic manipulations, known as the additive dynamic price of anarchy (ADPoA). While all iterative plurality winners have been shown to differ from truth by at most one initial vote, it is less understood how agents' welfare changes in equilibrium

In a dynamic matching market, such as a marriage or job market, how should agents balance accepting a proposed match with the cost of continuing their search? We consider this problem in a discrete setting, in which agents have cardinal values and finite lifetimes, and proposed matches are random. We seek to quantify how well the agents can do. We provide upper and lower bounds on the collective losses

We propose a new architecture to approximately learn incentive compatible, revenue-maximizing auctions from sampled valuations. Our architecture uses the Sinkhorn algorithm to perform a differentiable bipartite matching which allows the network to learn strategyproof revenue-maximizing mechanisms in settings not learnable by the previous RegretNet architecture. In particular, our architecture is able

The goal of this paper is to develop a generic framework for converting modern optimization algorithms into mechanisms where inputs come from self-interested agents. We focus on aggregating preferences from $n$ players in a context without money. Special cases of this setting include voting, allocation of items by lottery, and matching. Our key technical contribution is a new meta-algorithm we call

We study the problem of fair allocation of a set of indivisible items among agents with additive valuations, under cardinality constraints. In this setting the items are partitioned into categories, each with its own limit on the number of items it may contribute to any bundle. One example of such a problem is allocating seats in a multitrack conference. We consider the fairness measure known as the

In the optional prisoner's dilemma (OPD), players can choose to cooperate and defect as usual, but can also abstain as a third possible strategy. This strategy models the players' participation in the game and is a relevant aspect in many settings, e.g. social networks or opinion dynamics where abstention is an option during an election. In this paper, we provide a formulation of the OPD where we consider

We study fairness in house allocation, where $m$ houses are to be allocated among $n$ agents so that every agent receives one house. We show that maximizing the number of envy-free agents is hard to approximate to within a factor of $n^{1-\gamma}$ for any constant $\gamma>0$, and that the exact version is NP-hard even for binary utilities. Moreover, we prove that deciding whether a proportional allocation

We consider a model for repeated stochastic matching where compatibility is probabilistic, is realized the first time agents are matched, and persists in the future. Such a model has applications in the gig economy, kidney exchange, and mentorship matching. We ask whether a $decentralized$ matching process can approximate the optimal online algorithm. In particular, we consider a decentralized $stable$

We study the problem of allocating bailouts (stimulus, subsidy allocations) to people participating in a financial network subject to income shocks. We build on the financial clearing framework of Eisenberg and Noe that allows the incorporation of a bailout policy that is based on discrete bailouts motivated by the types of stimulus checks people receive around the world as part of COVID-19 economical

Generative Adversarial Network, as a promising research direction in the AI community, recently attracts considerable attention due to its ability to generating high-quality realistic data. GANs are a competing game between two neural networks trained in an adversarial manner to reach a Nash equilibrium. Despite the improvement accomplished in GANs in the last years, there remain several issues to

Public goods games represent insightful settings for studying incentives for individual agents to make contributions that, while costly for each of them, benefit the wider society. In this work, we adopt the perspective of a central planner with a global view of a network of self-interested agents and the goal of maximizing some desired property in the context of a best-shot public goods game. Existing

Bayesian persuasion studies how an informed sender should partially disclose information to influence the behavior of a self-interested receiver. Classical models make the stringent assumption that the sender knows the receiver's utility. This can be relaxed by considering an online learning framework in which the sender repeatedly faces a receiver of an unknown, adversarially selected type. We study

In this paper, we introduce a game that allows one to assess the potential loss of efficiency induced by a decentralized control or local management of a global epidemic. Each player typically represents a region or a country which is assumed to choose its control action to implement a tradeoff between socioeconomic aspects and the health aspect. We conduct the Nash equilibrium analysis of this game

In imperfect-information games, subgame solving is significantly more challenging than in perfect-information games, but in the last few years, such techniques have been developed. They were the key ingredient to the milestone of superhuman play in no-limit Texas hold'em poker. Current subgame-solving techniques analyze the entire common-knowledge closure of the player's current information set, that

In online advertising, auto-bidding has become an essential tool for advertisers to optimize their preferred ad performance metrics by simply expressing the high-level campaign objectives and constraints. Previous works consider the design of auto-bidding agents from the single-agent view without modeling the mutual influence between agents. In this paper, we instead consider this problem from the

We propose a practical approach to computing market prices and allocations via a deep reinforcement learning policymaker agent, operating in an environment of other learning agents. Compared to the idealized market equilibrium outcome -- which we use as a benchmark -- our policymaker is much more flexible, allowing us to tune the prices with regard to diverse objectives such as sustainability and resource

Participatory budgeting is a democratic process for allocating funds to projects based on the votes of members of the community. However, most input methods of voters' preferences prevent the voters from expressing complex relationships among projects, leading to outcomes that do not reflect their preferences well enough. In this paper, we propose an input method that begins to address this challenge

Before chess came to Northern Europe there was Tafl, a family of asymmetric strategy board games associated strongly with the Vikings. The purpose of this paper is to study the combinatorial state-space complexity of an Irish variation of Tafl called Brandubh. Brandubh was chosen because of its asymmetric goals for the two players, but also its overall complexity well below that of chess, which should

We study Nash equilibria in the network creation game of Fabrikant et al.[10]. In this game a vertex can buy an edge to another vertex for a cost of $\alpha$, and the objective of each vertex is to minimize the sum of the costs of the edges it purchases plus the sum of the distances to every other vertex in the resultant network. A long-standing conjecture states that if $\alpha\ge n$ then every Nash

We study a dynamic model of Bayesian persuasion in sequential decision-making settings. An informed principal observes an external parameter of the world and advises an uninformed agent about actions to take over time. The agent takes actions in each time step based on the current state, the principal's advice/signal, and beliefs about the external parameter. The action of the agent updates the state

We study the revenue guarantees and approximability of item pricing. Recent work shows that with $n$ heterogeneous items, item-pricing guarantees an $O(\log n)$ approximation to the optimal revenue achievable by any (buy-many) mechanism, even when buyers have arbitrarily combinatorial valuations. However, finding good item prices is challenging -- it is known that even under unit-demand valuations

In the Learning to Price setting, a seller posts prices over time with the goal of maximizing revenue while learning the buyer's valuation. This problem is very well understood when values are stationary (fixed or iid). Here we study the problem where the buyer's value is a moving target, i.e., they change over time either by a stochastic process or adversarially with bounded variation. In either case

Many real-world systems possess a hierarchical structure where a strategic plan is forwarded and implemented in a top-down manner. Examples include business activities in large companies or policy making for reducing the spread during pandemics. We introduce a novel class of games that we call structured hierarchical games (SHGs) to capture these strategic interactions. In an SHG, each player is represented

In this paper, we present a distributed resource allocation mechanism in cognitive radio networks, based on a new coopeti-tion methodology, which combines advantages of nodes competition and cooperation. We postulate that this new method allows for fully distributed resource management between cognitive radio devices. The presented framework is generic, however, we consider it for the application in

Measuring and promoting policy diversity is critical for solving games with strong non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). With that in mind, maintaining a pool of diverse policies via open-ended learning is an attractive solution, which can generate auto-curricula to avoid being exploited. However, in conventional open-ended

We present a novel control-theoretic understanding of online optimization and learning in games, via the notion of passivity. Passivity is a fundamental concept in control theory, which abstracts energy conservation and dissipation in physical systems. It has become a standard tool in analysis of general feedback systems, to which game dynamics belong. Our starting point is to show that all continuous-time

Distributed artificial intelligence (DAI) studies artificial intelligence entities working together to reason, plan, solve problems, organize behaviors and strategies, make collective decisions and learn. This Ph.D. research proposes a principled Multi-Agent Systems (MAS) cooperation framework, Self-Adaptive Swarm System (SASS), to bridge the fourth level automation gap between perception, communication

Machine learning algorithms often make decisions on behalf of agents with varied and sometimes conflicting interests. In domains where agents can choose to take their own action or delegate their action to a central mediator, an open question is how mediators should take actions on behalf of delegating agents. The main existing approach uses delegating agents to punish non-delegating agents in an attempt

The conflict between individual and collective interests is in the heart of every social dilemmas established by evolutionary game theory. We cannot avoid these conflicts but sometimes we may choose which interaction framework to use as a battlefield. For instance some people like to be part of a larger group while other persons prefer to interact in a more personalized, individual way. Both attitudes

Motivated by packet routing in computer networks, online queuing systems are composed of queues receiving packets at different rates. Repeatedly, they send packets to servers, each of them treating only at most one packet at a time. In the centralized case, the number of accumulated packets remains bounded (i.e., the system is \textit{stable}) as long as the ratio between service rates and arrival

Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids, i.e., the wining price is fixed, leading to poor performance of the derived solution. Although a few studies use multi-agent reinforcement learning to set up a cooperative

Game theoretic approaches have gained traction as a robust methodology for designing distributed local algorithms that induce a desired overall system configuration in a multi-agent setting. However, much of the emphasis in these approaches is on providing asymptotic guarantees on the performance of network of agents, and there is a gap in the study of efficiency guarantees along transients of these

We prove that every repeated game with countably many players, finite action sets, and tail-measurable payoffs admits an $\epsilon$-equilibrium, for every $\epsilon > 0$.

We study the network pricing problem where the leader maximizes their revenue by determining the optimal amounts of tolls to charge on a set of arcs, under the assumption that the followers will react rationally and choose the shortest paths to travel. Many distinct single-level reformulations to this bilevel optimization program have been proposed, however, their relationship has not been established

We study truthful mechanisms for allocation problems in graphs, both for the minimization (i.e., scheduling) and maximization (i.e., auctions) setting. The minimization problem is a special case of the well-studied unrelated machines scheduling problem, in which every given task can be executed only by two pre-specified machines in the case of graphs or a given subset of machines in the case of hypergraphs

In e-commerce advertising, it is crucial to jointly consider various performance metrics, e.g., user experience, advertiser utility, and platform revenue. Traditional auction mechanisms, such as GSP and VCG auctions, can be suboptimal due to their fixed allocation rules to optimize a single performance metric (e.g., revenue or social welfare). Recently, data-driven auctions, learned directly from auction

We propose a novel variant of the \emph{multiplicative weights update method} with forward-looking best-response strategies, that guarantees last-iterate convergence for \emph{zero-sum games} with a unique \emph{Nash equilibrium}. Particularly, we show that the proposed algorithm converges to an $\eta^{1/\rho}$-approximate Nash equilibrium, with $\rho > 1$, by decreasing the Kullback-Leibler divergence

In this article, we study whether people in the position of describing a decision problem to decision-makers exploit this opportunity for their benefit, by choosing descriptions that may be potentially beneficial for themselves. To this end, we design, pre-register, and conduct an experiment in which dictator game recipients are asked to choose the instructions used to introduce the game to dictators

The study of approximate mechanism design for facility location problems has been in the center of research at the intersection of artificial intelligence and economics for the last decades, largely due to its practical importance in various domains, such as social planning and clustering.At a high level, the goal is to design mechanisms to select a set of locations on which to build a set of facilities

A growing body of work in game theory extends the traditional Stackelberg game to settings with one leader and multiple followers who play a Nash equilibrium. Standard approaches for computing equilibria in these games reformulate the followers' best response as constraints in the leader's optimization problem. These reformulation approaches can sometimes be effective, but often get trapped in low-quality

The design of optimal auctions is a problem of interest in economics, game theory and computer science. Despite decades of effort, strategyproof, revenue-maximizing auction designs are still not known outside of restricted settings. However, recent methods using deep learning have shown some success in approximating optimal auctions, recovering several known solutions and outperforming strong baselines

Recent advances in multi-task peer prediction have greatly expanded our knowledge about the power of multi-task peer prediction mechanisms. Various mechanisms have been proposed in different settings to elicit different types of information. But we still lack understanding about when desirable mechanisms will exist for a multi-task peer prediction problem. In this work, we study the elicitability of

We consider a setting in which agents are allocated land plots and they have additive preferences over which plot they get and who their neighbor is. Strategyproofness, Pareto optimality, and individual rationality are three fundamental properties in economic design. We present two impossibility results showing that the three properties are incompatible in this context.

We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, where agents make decisions without coordination by a centralized controller, but only based on their own payoffs and local actions executed. The agents need not observe the opponent's actions or payoffs, possibly being even

Crowdsourcing-based content moderation is a platform that hosts content moderation tasks for crowd workers to review user submissions (e.g. text, images and videos) and make decisions regarding the admissibility of the posted content, along with a gamut of other tasks such as image labeling and speech-to-text conversion. In an attempt to reduce cognitive overload at the workers and improve system efficiency

It is often beneficial for agents to pool their resources in order to better accommodate fluctuations in individual demand. Many multi-round resource allocation mechanisms operate in an online manner: in each round, the agents specify their demands for that round, and the mechanism determines a corresponding allocation. In this paper, we focus instead on the offline setting in which the agents specify

We study the problem of allocating indivisible goods among agents in a fair and economically efficient manner. In this context, the Nash social welfare--defined as the geometric mean of agents' valuations for their assigned bundles--stands as a fundamental measure that quantifies the extent of fairness of an allocation. Focusing on instances in which the agents' valuations have binary marginals, we

Automated decision-making tools increasingly assess individuals to determine if they qualify for high-stakes opportunities. A recent line of research investigates how strategic agents may respond to such scoring tools to receive favorable assessments. While prior work has focused on the short-term strategic interactions between a decision-making institution (modeled as a principal) and individual decision-subjects

It is well known that two-sided markets are unfair in a number of ways. For instance, female workers at Uber earn less than their male colleagues per mile driven. Similar observations have been made for other minority subgroups in other two-sided markets. Here, we suggest a novel market-clearing mechanism for two-sided markets, which promotes equalisation of the pay per hour worked across multiple

Recently, Optimistic Multiplicative Weights Update (OMWU) was proven to be the first constant step-size algorithm in the online no-regret framework to enjoy last-iterate convergence to Nash Equilibria in the constrained zero-sum bimatrix case, where weights represent the probabilities of playing pure strategies. We introduce the second such algorithm, \textit{Consensus MWU}, for which we prove local

The geometric median of a tuple of vectors is the vector that minimizes the sum of Euclidean distances to the vectors of the tuple. Interestingly, the geometric median can also be viewed as the equilibrium of a process where each vector of the tuple pulls on a common decision point with a unitary force towards them, promoting the "one voter, one unit force" fairness principle. In this paper, we analyze

This problem, recently proposed by Hosseini et al. (2020), captures several natural scenarios such as the allocation of multiple facilities over time where each agent can utilize at most one facility simultaneously, and the allocation of tasks over time where each agent can perform at most one task simultaneously. We establish the existence of an envy-free multi-division that is both non-overlapping

We define a model of interactive communication where two agents with private types can exchange information before a game is played. The model contains Bayesian persuasion as a special case of a one-round communication protocol. We define message complexity corresponding to the minimum number of interactive rounds necessary to achieve the best possible outcome. Our main result is that for bilateral

Simple binary-state coordination models are widely used to study collective socio-economic phenomena such as the spread of innovations or the adoption of products on social networks. The common trait of these systems is the occurrence of large-scale coordination events taking place abruptly, in the form of a cascade process, as a consequence of small perturbations of an apparently stable state. The

A patient seller aims to sell a good to an impatient buyer (i.e., one who discounts utility over time). The buyer will remain in the market for a period of time $T$, and her private value is drawn from a publicly known distribution. What is the revenue-optimal pricing-curve (sequence of (price, time) pairs) for the seller? Is randomization of help here? Is the revenue-optimal pricing-curve computable