arXiv subjects

Sven Seuken

Publications and source records attributed to Sven Seuken.

At least 37 records · Page 2Linked to original sources

arXiv2022

Market Design for Drone Traffic Management

The rapid development of drone technology is leading to more and more use cases being proposed. In response, regulators are drawing up drone traffic management frameworks. However, to design solutions that are efficient, fair, simple, non-manipulable, and scalable, we need market design and AI expertise. To this end, we introduce the drone traffic management problem as a new research challenge to the market design and AI communities. We present five design desiderata that we have derived from our interviews with stakeholders from the regulatory side as well as from public and private enterprises. Finally, we provide an overview of the solution space to point out possible directions for future research.

cs.GT↗

arXiv2021

The Cost of Simple Bidding in Combinatorial Auctions

We study a class of manipulations in combinatorial auctions where bidders fundamentally misrepresent what goods they are interested in. Prior work has largely assumed that bidders only submit bids on their bundles of interest, which we call simple bidding: strategizing over the bid amounts, but not the bundle identities. However, we show that there exists an entire class of auction instances for which simple bids are never optimal in Bayes-Nash equilibrium, always being strictly dominated by complex bids (where bidders bid on goods they are not interested in). We show this result for the two most widely used auction mechanisms: first price and VCG-nearest. We also explore the structural properties of the winner determination problem that cause this phenomenon, and we use the insights gained to investigate how impactful complex bidding may be. We find that, in the worst case, a bidder's optimal complex bid may require bidding on an exponential number of bundles, even if the bidder is interested only in a single good. Thus, this phenomenon can greatly impact the auction's outcome and should not be ignored by bidders and auction designers alike.

cs.GT↗

arXiv2021

Machine Learning-powered Iterative Combinatorial Auctions

We present a machine learning-powered iterative combinatorial auction (MLCA). The main goal of integrating machine learning (ML) into the auction is to improve preference elicitation, which is a major challenge in large combinatorial auctions (CAs). In contrast to prior work, our auction design uses value queries instead of prices to drive the auction. The ML algorithm is used to help the auction decide which value queries to ask in every iteration. While using ML inside a CA introduces new challenges, we demonstrate how we obtain a design that is individually rational, satisfies no-deficit, has good incentives, and is computationally practical. We benchmark our new auction against the well-known combinatorial clock auction (CCA). Our results indicate that, especially in large domains, MLCA can achieve significantly higher allocative efficiency than the CCA, even with only a small number of value queries.

cs.GT↗

arXiv2021

Shapley-Based Core-Selecting Payment Rules

In this research note, we lay some groundwork for analyzing the manipulability of core-selecting payment rules in combinatorial auctions. In particular, we focus on payment rules based on the bidders' Shapley values. We define a sensitivity metric, and provide analytical results for this metric in LLG, for six different payment vectors used as reference points for minimum-revenue core-selecting payment rules. We furthermore show how this sensitivity affects the derivative of the resulting payment rules.

cs.GT↗

arXiv2020

On the cluster admission problem for cloud computing

Cloud computing providers face the problem of matching heterogeneous customer workloads to resources that will serve them. This is particularly challenging if customers, who are already running a job on a cluster, scale their resource usage up and down over time. The provider therefore has to continuously decide whether she can add additional workloads to a given cluster or if doing so would impact existing workloads' ability to scale. Currently, this is often done using simple threshold policies to reserve large parts of each cluster, which leads to low efficiency (i.e., low average utilization of the cluster). We propose more sophisticated policies for controlling admission to a cluster and demonstrate that they significantly increase cluster utilization. We first introduce the cluster admission problem and formalize it as a constrained Partially Observable Markov Decision Process (POMDP). As it is infeasible to solve the POMDP optimally, we then systematically design admission policies that estimate moments of each workload's distribution of future resource usage. Via extensive simulations grounded in a trace from Microsoft Azure, we show that our admission policies lead to a substantial improvement over the simple threshold policy. We then show that substantial further gains are possible if high-quality information is available about arriving workloads. Based on this, we propose an information elicitation approach to incentivize users to provide this information and simulate its effects.

cs.DC↗

arXiv2020

Partial Strategyproofness: Relaxing Strategyproofness for the Random Assignment Problem

We present partial strategyproofness, a new, relaxed notion of strategyproofness for studying the incentive properties of non-strategyproof assignment mechanisms. Informally, a mechanism is partially strategyproof if it makes truthful reporting a dominant strategy for those agents whose preference intensities differ sufficiently between any two objects. We demonstrate that partial strategyproofness is axiomatically motivated and yields a parametric measure for "how strategyproof" an assignment mechanism is. We apply this new concept to derive novel insights about the incentive properties of the probabilistic serial mechanism and different variants of the Boston mechanism.

cs.GT↗

arXiv2020

Computing Bayes-Nash Equilibria in Combinatorial Auctions with Verification

We present a new algorithm for computing pure-strategy $\varepsilon$-Bayes-Nash equilibria ($\varepsilon$-BNEs) in combinatorial auctions with continuous value and action spaces. An essential innovation of our algorithm is to separate the algorithm's search phase (for finding the $\varepsilon$-BNE) from the verification phase (for computing the $\varepsilon$). Using this approach, we obtain an algorithm that is both very fast and provides theoretical guarantees on the $\varepsilon$ it finds. Our main technical contribution is a verification method which allows us to upper bound the $\varepsilon$ across the whole continuous value space without making assumptions about the mechanism. Using our algorithm, we can now compute $\varepsilon$-BNEs in multi-minded domains that are significantly more complex than what was previously possible to solve. We release our code under an open-source license to enable researchers to perform algorithmic analyses of auctions, to enable bidders to analyze different strategies, and to facilitate many other applications.

cs.GT↗

arXiv2020

Revenue Maximization for Consumer Software: Subscription or Perpetual License?

We study the revenue maximization problem of a publisher selling consumer software. We assume that the publisher sells either traditional perpetual licenses, subscription licenses, or both. For our analysis, we employ a game-theoretic model, which enables us to derive the users' equilibrium strategies and the publisher's optimal pricing strategy. Via extensive numerical evaluations, we then demonstrate the sizable impact different pricing strategies have on the publisher's revenue, and we provide comparative statics for the most important settings parameters. Although in practice, many publishers still only sell perceptual licenses, we find that offering a subscription license in addition to a perpetual license typically (but not always) leads to significantly higher revenue than only selling either type of license on its own.

cs.GT↗

arXiv2020

Local Sufficiency for Partial Strategyproofness

In (Mennle and Seuken, 2017), we have introduced partial strategyproofness, a new, relaxed notion of strategyproofness, to study the incentive properties of non-strategyproof assignment mechanisms. In this paper, we present results pertaining to local sufficiency for partial strategyproofness: We show that, for any r in [0,1], r-local partial strategyproofness implies r^2-partial strategyproofness, and we show that this is the tightest polynomial bound for which a guarantee can be proven. Our results unify the two prior local sufficiency results for strategyproofness (Carroll, 2012) and lexicographic dominance-strategyproofness (Cho, 2012).

cs.GT↗

arXiv2020

Two New Impossibility Results for the Random Assignment Problem

In this note, we prove two new impossibility results for random assignment mechanisms: Bogomolnaia and Moulin (2001) showed that no assignment mechanism can satisfy strategyproofness, ordinal efficiency, and symmetry at the same time, and Mennle and Seuken (2017) gave a decomposition of strategyproofness into the axioms swap monotonicity, upper invariance, and lower invariance. For our first impossibility result, we show that upper invariance, lower invariance, ordinal efficiency, and symmetry are incompatible. This refines the prior impossibility result because it relaxes swap monotonicity. For our second impossibility result, we show that no assignment mechanism satisfies swap monotonicity, lower invariance, ordinal efficiency, anonymity, neutrality, and non-bossiness. By contrasts, the Probabilistic Serial (PS) mechanism that Bogomolnaia and Moulin (2001) introduced, satisfies these axioms when lower invariance is replaced by upper invariance. It follows that there cannot exists a lower invariant counterpart to PS.

cs.GT↗

arXiv2020

An Axiomatic Decomposition of Strategyproofness for Ordinal Mechanism with Indifferences

We study mechanism which operate on ordinal preference information (i.e., rank ordered lists of alternatives) on the full domain of weak preferences that admits indifferences. We present a novel decomposition of strategyproofness into three axioms: separation monotonic, separation upper invariant, and separation lower invariant. Each axiom is a natural restriction on how mechanisms can react when agents change their opinion about the relative ranking of any two adjacently ranked groups of alternatives. Our result extends a result from (Mennle and Seuken, 2017), a decomposition of strategyproofness for strict preferences, to the full domain that includes weak preferences.

cs.GT↗

arXiv2020

The Competitive Effects of Variance-based Pricing

In many markets, like electricity or cloud computing markets, providers incur large costs for keeping sufficient capacity in reserve to accommodate demand fluctuations of a mostly fixed user base. These costs are significantly affected by the unpredictability of the users' demand. Nevertheless, standard mechanisms charge fixed per-unit prices that do not depend on the variability of the users' demand. In this paper, we study a variance-based pricing rule in a two-provider market setting and perform a game-theoretic analysis of the resulting competitive effects. We show that an innovative provider who employs variance-based pricing can choose a pricing strategy that guarantees himself a higher profit than using fixed per-unit prices for any individually rational response of a provider playing a fixed pricing strategy. We characterize all equilibria for the setting where both providers employ variance-based pricing strategies. We find that, while in equilibrium, the profits of the providers may increase or decrease depending on their cost functions, social welfare always weakly increases.

cs.GT↗

arXiv2019

Monotonic and Non-Monotonic Solution Concepts for Generalized Circuits

Generalized circuits are an important tool in the study of the computational complexity of equilibrium approximation problems. However, in this paper, we reveal that they have a conceptual flaw, namely that the solution concept is not monotonic. By this we mean that if $\varepsilon < \varepsilon'$, then an $\varepsilon$-approximate solution for a certain generalized circuit is not necessarily also an $\varepsilon'$-approximate solution. The reason for this non-monotonicity is the way Boolean operations are modeled. We illustrate that non-monotonicity creates subtle technical issues in prior work that require intricate additional arguments to circumvent. To eliminate this problem, we show that the Boolean gates are a redundant feature: one can simulate stronger, monotonic versions of the Boolean gates using the other gate types. Arguing at the level of these stronger Boolean gates eliminates all of the aforementioned issues in a natural way. We hope that our results will enable new studies of sub-classes of generalized circuits and enabler simpler and more natural reductions from generalized circuits to other equilibrium search problems.

cs.CC↗

arXiv2019

Fast Iterative Combinatorial Auctions via Bayesian Learning

Iterative combinatorial auctions (CAs) are often used in multi-billion dollar domains like spectrum auctions, and speed of convergence is one of the crucial factors behind the choice of a specific design for practical applications. To achieve fast convergence, current CAs require careful tuning of the price update rule to balance convergence speed and allocative efficiency. Brero and Lahaie (2018) recently introduced a Bayesian iterative auction design for settings with single-minded bidders. The Bayesian approach allowed them to incorporate prior knowledge into the price update algorithm, reducing the number of rounds to convergence with minimal parameter tuning. In this paper, we generalize their work to settings with no restrictions on bidder valuations. We introduce a new Bayesian CA design for this general setting which uses Monte Carlo Expectation Maximization to update prices at each round of the auction. We evaluate our approach via simulations on CATS instances. Our results show that our Bayesian CA outperforms even a highly optimized benchmark in terms of clearing percentage and convergence speed.

cs.GT↗

arXiv2019

The Computational Complexity of Financial Networks with Credit Default Swaps

The 2008 financial crisis has been attributed to "excessive complexity" of the financial system due to financial innovation. We employ computational complexity theory to make this notion precise. Specifically, we consider the problem of clearing a financial network after a shock. Prior work has shown that when banks can only enter into simple debt contracts with each other, then this problem can be solved in polynomial time. In contrast, if they can also enter into credit default swaps (CDSs), i.e., financial derivative contracts that depend on the default of another bank, a solution may not even exist. In this work, we show that deciding if a solution exists is NP-complete if CDSs are allowed. This remains true if we relax the problem to $\varepsilon$-approximate solutions, for a constant $\varepsilon$. We further show that, under sufficient conditions where a solution is guaranteed to exist, the approximate search problem is PPAD-complete for constant $\varepsilon$. We then try to isolate the "origin" of the complexity. It turns out that already determining which banks default is hard. Further, we show that the complexity is not driven by the dependence of counterparties on each other, but rather hinges on the presence of so-called naked CDSs. If naked CDSs are not present, we receive a simple polynomial-time algorithm. Our results are of practical importance for regulators' stress tests and regulatory policy.

q-fin.RM↗

arXiv2018

FedMark: A Marketplace for Federated Data on the Web

The Web of Data (WoD) has experienced a phenomenal growth in the past. This growth is mainly fueled by tireless volunteers, government subsidies, and open data legislations. The majority of commercial data has not made the transition to the WoD, yet. The problem is that it is not clear how publishers of commercial data can monetize their data in this new setting. Advertisement, which is one of the main financial engines of the World Wide Web, cannot be applied to the Web of Data as such unwanted data can easily be filtered out, automatically. This raises the question how the WoD can (i) maintain its grow when subsidies disappear and (ii) give commercial data providers financial incentives to share their wealth of data. In this paper, we propose a marketplace for the WoD as a solution for this data monetization problem. Our approach allows a customer to transparently buy data from a combination of different providers. To that end, we introduce two different approaches for deciding which data elements to buy and compare their performance. We also introduce FedMark, a prototypical implementation of our marketplace that represents a first step towards an economically viable WoD beyond subsidies.

cs.DB↗

arXiv2017

Hybrid Mechanisms: Trading off Strategyproofness and Efficiency of Random Assignment Mechanisms

Severe impossibility results restrict the design of strategyproof random assignment mechanisms, and trade-offs are necessary when aiming for more demanding efficiency requirements, such as ordinal or rank efficiency. We introduce hybrid mechanisms, which are convex combinations of two component mechanisms. We give a set of conditions under which such hybrids facilitate a non-degenerate trade-off between strategyproofness (in terms of partial strategyproofness) and efficiency (in terms of dominance). This set of conditions is tight in the sense that trade-offs may become degenerate if any of the conditions are dropped. Moreover, we give an algorithm for the mechanism designer's problem of determining a maximal mixing factor. Finally, we prove that our construction can be applied to mix Random Serial Dictatorship with Probabilistic Serial, as well as with the adaptive Boston mechanism, and we illustrate the efficiency gains numerically.

cs.GT↗

arXiv2017

Trade-offs in School Choice: Comparing Deferred Acceptance, the Naive and the Classic Boston Mechanism

The three most common school choice mechanisms are the Deferred Acceptance mechanism (DA), the classic Boston mechanism (BM), and a variant of the Boston mechanism where students automatically skip exhausted schools, which we call the adaptive Boston mechanism (ABM). Assuming truthful reporting, we compare student welfare under these mechanisms both from a conceptual and from a quantitative perspective: We first show that, BM rank dominates DA whenever they are comparable; and via limit arguments and simulations we show that ABM yields intermediate student welfare between BM and DA. Second, we perform computational experiments with preference data from the high school match in Mexico City. We find that student welfare (in terms of rank transitions) is highest under BM, intermediate under ABM, and lowest under DA. BM, ABM, and DA can thus be understood to form a hierarchy in terms of student welfare. In contrast, in (Mennle and Seuken, 2017), we have found that the same mechanisms also form a hierarchy in terms of incentives for truthtelling that points in the opposite direction. A decision between them therefore involves an implicit trade-off between incentives and student welfare.

cs.GT↗