Papers

We study the strategic impact of ambiguity through the channel of higher-order beliefs. We show that even small amounts of prior ambiguity about game payoffs can generate arbitrarily large amounts of higher-order ambiguity. This gives rise to a novel form of contagion: vanishingly small payoff ambiguity can select “secure” actions (e.g., non-participation) as the unique equilibrium outcome even when those actions are almost dominated. We highlight two main implications. First, classical robustness results under probabilistic uncertainty break down under ambiguity when players can deviate to secure actions. Second, if a designer can introduce small amounts of payoff ambiguity into a game, this can serve as a powerful tool for unique implementation.

We study how competition among biased news sources affects information and welfare when sources can misrepresent facts at a cost. Monopolistic and competitive market structures admit many equilibria. We develop a common belief-based selection criterion that applies to both and makes welfare comparisons possible. Under the refined outcomes, adding an oppositely biased source improves the receiver's welfare when that source faces sufficiently high misreporting costs. Competition disciplines the incumbent while introducing a few distortions of its own. Better information need not increase total welfare, and distorted advice from a monopolist can raise total welfare. Competition may improve decision-making without being socially beneficial.

Platforms use rating bonuses and badges to reward good sellers. When ratings can be inflated, stronger rewards can instead weaken the information available to buyers. We study an initially informative rating system in which sellers can pay to raise their displayed score and buyers rationally account for manipulation. Manipulation costs and returns are common across qualities conditional on the honest rating. Under this restriction, credibility can fail to increase between adjacent scores only where the higher score earns an additional reward. Our main result concerns large top-rating bonuses. Once sellers choose only between keeping their honest rating and reaching the top, a larger bonus makes the equilibrium rating system less informative in Blackwell's order along either extremal equilibrium selection. Lower scores retain their honest quality composition but become rarer. As the bonus grows, almost everyone displays the top score, its credibility approaches the population average, and the value of rating information vanishes. Nevertheless, a nearly perfect score can remain more credible than a perfect one. We derive the rate of information loss for exponential manipulation costs and establish a budget-feasible exposure rule that avoids credibility reversals. The results suggest that platform evaluations should examine rating frequencies together with category credibility. Rational buyer skepticism can correct the interpretation of ratings without recovering the distinctions that manipulation has erased.

We study deterministic choice when the same decision maker is observed before and after a deliberative intervention that makes one of two fixed ordinal consequence dimensions more salient. Both choice modes are path independent. Ordinary choice respects two-dimensional dominance, while any binary reversal under fuller deliberation must favor the alternative that is strictly better on the emphasized dimension. We characterize exactly the admissible ordinary and full-horizon rankings. The characterization yields a protected partial order, sharp pairwise and menu-level identification, a signed restriction on menu-level choice changes, and an acyclicity test for incomplete observations. With an ordered sequence of deliberative modes, choices from any fixed menu form a monotone tradeoff path: every switch improves the emphasized dimension, worsens the other dimension, and an abandoned alternative cannot reappear. When the emphasized consequence order is strict, the admissible rankings have an equivalent Kemeny-Kendall representation. The framework is ordinal: it requires neither a cardinal tradeoff nor lexicographic priority, and it applies whenever deliberation gives greater emphasis to one of two fixed consequence dimensions.

We develop a unified approach to optimal grading in an all-pay contest in which a designer assigns a fixed vector of heterogeneous prizes to maximize expected total effort. The approach covers two information regimes and identifies a common principle: iron locally misordered incentive returns and assign prizes assortatively across the resulting grades. Under rank-only grading, assignments depend only on ordinal ranks. Ironing cumulative rank coefficients—via the least concave majorant or the pool-adjacent-violators algorithm—determines which adjacent ranks are pooled and which prizes are randomized within each grade. Under performance-contingent grading, assignments may depend on numerical effort. The optimum irons virtual ability, forms endogenous type grades, and assigns prize blocks assortatively across grades. A failing grade below a minimum passing effort and a collection of effort brackets implement the direct optimum while preserving full prize assignment.

A team-contest designer values output rather than expenditure; nonlinear conversion makes the distinction consequential. We study two non-pecuniary instruments in majority-rule contests decided by pairwise all-pay battles with private abilities: disclosing resolved outcomes and splitting the battle schedule into finer blocks. Neither changes a battle's average pivotality; each only redistributes it across histories. Under nested information structures, this redistribution makes equilibrium ability-scaled expenditure weakly more dispersed player by player without changing its mean; expected aggregate expenditure is invariant across all designs considered. The resulting convex-order comparison ranks expected total output: convex output costs favor no disclosure and coarser temporal structures, concave costs favor full disclosure and finer ones, and linear costs make both comparisons neutral. The rankings hold for finite-support and smooth continuous-type ability distributions. The mechanism extends to degree-zero component contest technologies with a unique equilibrium outcome distribution. No and full disclosure bound every admissible public garbling.

Consider the problem of designing a revenue-optimal auction mechanism when two heterogeneous items are sold to a single buyer having independent valuations over the items. The distributions of the buyer's valuation for the items are assumed to have densities that are positive, nondecreasing, and continuously differentiable on their support sets $[c_i,c_i+b_i]$ in the positive axis. I prove that the optimal mechanism is deterministic if at least one of the minimum valuations (i.e., either $c_1$ or $c_2$) is sufficiently high. I provide a method to calculate the threshold of $(c_1,c_2)$ beyond which the optimal mechanism is deterministic. I also provide a sufficient condition on the distributions of buyer's valuations for which the individual sale mechanism is optimal. I show that when $c_1$ is low and $c_2$ is high, it is optimal for the seller to sell item $2$ at the minimum valuation $c_2$, thus effectively reducing the problem to finding the optimal mechanism in the one-dimensional setting only for item $1$. I conjecture with promising preliminary results that this result can be extended to the three-item setting. Specifically, I conjecture that when $c_1$ and $c_2$ are low but $c_3$ is high, it is optimal for the seller to sell item $3$ at the minimum valuation $c_3$, thus effectively reducing the problem to finding the optimal mechanism in the two-dimensional setting for items $1$ and $2$.

We characterize the communication networks that ensure consensus in rational social learning under the sure-thing principle. A network ensures consensus if and only if it is pseudo-reciprocal, a property under which reciprocity may fail between individuals but holds at a coarser group level. Prior work has assumed message exchange to be bidirectional, yet such pairwise reciprocity proves largely dispensable. We show that a single bidirectional link can suffice, however large the population.

Rising interest rates can expose life insurers to surrender risk by reducing the market value of their assets and raising policyholders' outside returns. This paper develops a minimal model of an insurance-specific run mechanism in which strategic interaction arises because early surrenders can deplete the asset pool backing continuation values. We analyze a strategic surrender game in which a run is an equilibrium outcome determined jointly by asset values, contractual surrender claims, and payoff-dependent continuation benefits. The model yields closed-form interest-rate thresholds for fundamentals-driven and self-fulfilling runs. Thinner capitalization weakly lowers the joint-surrender cutoff. Continuation benefits raise surrender thresholds but can also create strategic complementarity.

As an extension of existing Bayesian persuasion framework with inadequate message mechanism, we study direct recommendation when a sender is bound by an installed information policy only with probability $\rho$, the realization of binding is hidden, and the receiver does not observe the persistent structural environment. The receiver first sees a payoff-neutral, nonmanipulable calibration sample and then faces a fresh, non-certified deployment interaction. In common, the calibration law identifies only the receiver-facing reduced form, not the latent binding and discretionary kernels. We characterize type-wise $\rho$-implementability, construct the receiver's posterior over the full deployment node, and prove a static direct-following implementation theorem. After every calibration history that passes a posterior-predictive obedience test, the deployment assessment is an exact perfect Bayesian equilibrium: Bayes consistency, receiver sequential rationality, sender sequential rationality, and off-path completion are all verified. Under finite-type separation, common recommendation support, and a positive obedience margin, the test activates such an equilibrium with high probability. Our results keep statistical failure probability distinct from equilibrium approximation. Finally, we embed the original robust value frontier, support-wise linear-programming algorithm, and binary-action fractional-knapsack specialization into this implementation framework

Objective functions (goodness criteria which have to be optimized) that are considered, for instance, in cluster analysis, factor analysis, (linear) structural equation modeling, (linear) regression, multidimensional scaling, choice theory, and utility theory, must be adequate, i.e. carefully adapted to the structure of the observed data. Adequateness of an objective function means, in our terminology, that (certain) transformations of its arguments, e.g. changes in the unit measures of the quantities involved, do not influence the solutions of the optimization procedure. In this paper we concentrate our attention on affine strictly increasing transformations and we also incorporate the case of continuous adequate objective functions accordingly. The characterization of adequate dissimilarity coefficients for interval scaled data shows the appropriateness of the concept of adequateness that is developed in this paper.

We compare statistical experiments when observations are inexpensive and can be acquired sequentially until the decision maker chooses to stop. We introduce two orders. Small-cost decision dominance asks which of two equally priced experiments is eventually preferred in every decision problem as the per-observation cost vanishes; large-budget stopping dominance asks which experiment can reproduce every terminal experiment attainable from the other under all sufficiently large expected-sample budgets. Our main result shows that, for generic pairs, the two orders coincide and are both characterized by strict dominance of every pairwise Kullback–Leibler divergence. The key step is a uniform exact-conversion theorem: any finite-output stopping policy based on one experiment can be reproduced exactly using another, with first-order expected-sample requirements determined by pairwise KL rates and a square-root remainder that is uniform over policies.

Are simple delegation rules optimal under ambiguity? We study delegation when the principal knows the mean, but not the distribution, of the agent's private information. In a parsimonious quadratic constant-bias environment, the robustly optimal randomized mechanism is a random cap: the principal draws and reveals an upper bound, below which the agent chooses freely. Randomization strictly outperforms every deterministic cap by hedging against cap-specific worst-case distributions. We characterize random caps through a nondecreasing and concave expected-action rule and construct the solution using a saddle-point approach. The worst-case distribution features an exponential survival function over its continuous region and an atom at the upper endpoint. Under regularity conditions, the result extends to convex-order ambiguity. Moreover, when the mean is below the agent's bias, an optimum can be implemented by supplementing the random cap with an incentive-neutral outcome lottery, while pure random caps are strictly suboptimal.

We study one-dimensional screening when the Spence-Mirrlees condition fails along a monotone dividing curve, on which all types value marginal output equally. A single ratio, marginal distortion over marginal rent, governs the problem. When the relaxed solution stays in the positive region, non-decreasing optima in the positive single-crossing region are continuous if the ratio increases in the decision. When it crosses a flat curve and marginal rents are separable, every continuous contract is improved by a jump. When it crosses a strictly monotone curve, a contract that pools and jumps continues along the mirror of the pool if the ratio does not increase along it. Optimality among all implementable allocations, deterministic or random, is proved by a measure on the binding constraints whose weights are the same ratio; with constant curvatures and no crossing, it is also necessary. As applications, we solve problems of procurement and nonlinear pricing.

I study why some groups—polities and organizations alike—sustain independent judgment while others fall into conformity traps. Social approval can suppress not only the expression of independent judgment but also the upstream practice that keeps such judgment available: maintaining judgment generates visible questioning, and observers cannot distinguish diligence from opposition. Because suspicion falls when questioning is common, the same desire for approval can sustain a questioning culture or a conformity trap. The model separates maintaining judgment from acting on it when novelty arrives. When the decision to act is uniquely determined, I give primitive conditions for coexistence; in a logit–proportional benchmark, a single inequality is necessary and sufficient. The principal contribution is dynamic. Under staggered revision the stock of judgment is inherited: protecting dissent releases existing judgment at once—with negative expected adaptive value on impact in a stationary culture below a break-even competence threshold—whereas rebuilding the stock is constrained by turnover. A monotone operator constructs the extremal perfect-foresight paths from every inherited state. When recovery under every admissible continuation is attainable, two cutoffs classify inherited states—recovery impossible, expectation-dependent, or assured—and a focus condition at the unstable culture strictly separates them, opening a band of states where expectations select the long-run culture. Turnover then yields sharp physical duration bounds, within temporary direct formation support, for making recovery possible or robust. A fully coupled interval-certified example verifies coexistence, the band, and the distinct output and welfare implications.

The Plurality rule is vulnerable to vote splitting between similar alternatives. Defying conventional wisdom, we characterize the Plurality rule through a specific type of clone independence condition. We further introduce the notion of a one-parameter family of $p$-Clone Resistance ($p$-CR), and examine the property within the class of scoring rules. For $p \in (0,1)$, nontrivial rules exist with at most three alternatives, but only the Trivial rule generally satisfies the condition.

We study coalitional manipulation of interval-valued social choice correspondences on the single-peaked domain. In the single-valued model, strategy-proofness and group strategy-proofness coincide within the standard class of peaks-only social choice functions, so generalized median voter rules retain their robustness to coalitional manipulation. This equivalence breaks down once the outcome is allowed to be set-valued: generalized median correspondences may be strategy-proof while remaining vulnerable to coordinated deviations. We show that, among generalized median correspondences allowing genuine set-valued choice, pairwise strategy-proofness already forces anonymity. With voter sovereignty, this restriction becomes sharp and characterizes target set correspondences. Thus, the target-set structure emerges as the form of set-valued flexibility compatible with pairwise coalitional robustness.

This paper develops a revolving-door model in which a regulator designs policy signals that affect a regulated firm's capital structure while holding an implicit career option to leave public service for the regulated firm or its advisers. The model has three linked mechanisms. First, regulatory signals alter the firm's pricing, leverage, and risk choices by changing the tradeoff between consumer surplus and firm profit. Second, because the regulator's outside payoff is convex in regulated-firm value, the career option rises with firm value, leverage, and signal-induced volatility. Third, when signal-induced volatility raises the option vega of firm equity, the same mechanism can increase tail risk and reduce distance to default. A proof-of-concept calibration illustrates leverage-vega warning regions and shows how a regulator-induced signal can move a firm from a go-leverage region into an early-warning or crash-risk region. The calibration includes maturity comparisons, sensitivity grids over compensation convexity and initial leverage, a bank-like parameter anchor, stochastic signal simulations, and a stopping-horizon diagnostic. Evidence from federal payroll data on post-employment restrictions supports the career-option primitive by showing that limits on revolving-door opportunities affect post-agency pay. The exercises also organize historical regulatory failures: Lehman Brothers as a regulatory-vacuum case, Silicon Valley Bank as a distorted-signal and weak-supervision case, and Signature Bank as a converted-signal case involving post-public-service incentives, lighter oversight, rapid growth, uninsured-deposit exposure, and tail risk. The model does not predict collapse dates; it identifies conditions under which regulatory forbearance, weak debt penalties, and career-option incentives can delay oversight until firms cross a leverage-vega warning threshold.

This paper presents a framework for stable matching markets that accommodates the peer-dependent preferences employed in empirical work. We show the existence of a stable matching in a continuum economy and of an approximately stable matching in a large finite sampled economy under assumptions satisfied by standard empirical specifications. The analysis builds on a tractable characterization of stable matchings with peer-dependent preferences in terms of supply and demand equations along with a rational-expectations condition.

We examine how agents learn when information from original sources only reaches them after noisy relay. A receiver learns if and only if they have access to sufficiently many chains of noisy relay and they perfectly understand the noise process. However, even slight uncertainty over message mutation rates makes learning from long chains impossible, no matter how many independent sources are accessed.

We introduce a general, easy-to-implement AI-based modeling technique for analyzing human behavior. A key feature of this approach, which contrasts with existing modeling techniques, is that it combines the flexibility and interpretability of natural language with a mathematical structure that can be fitted to data and easily analyzed. We assign a large language model a vector of trait intensities-a type vector-and then ask it to choose actions across settings in which we observe human choices. For instance, the type vector (2,4) could correspond to "You are a player characterized by the following profile: Altruism: 2 out of 5, Risk Aversion: 4 out of 5," after which it is asked to make choices. We can then vary the traits (e.g., Altruism, Fairness, Trust,...) and values (e.g., 1-5) to minimize distance to human choices. We illustrate the method by applying it to model 119,147 decisions made by 78,657 subjects from more than 35 countries across 10 classic economic game roles. We find that human behavior can be closely matched using three dimensions: Risk Aversion, Strategic Sophistication, and Trust. The type vectors needed to fit individuals across games cluster into fewer than a dozen groups, with substantial variation in fit across subjects. Moreover, the individual type vectors can predict behavior in held-out games with different rules and available actions. More broadly, this new modeling method is highly generalizable and interpretable: we can input any vector of traits and use them to model behavior across any setting

We study a dynamic coalition-formation process in the tradition of Konishi and Ray (2003): players repeatedly form and dissolve binding agreements, evaluate states by discounted long-term expected payoffs, and hold self-confirming beliefs about the process. States and payoff sharing follow Heitzig and Kornek (2018): a state is a hierarchy of nested agreements, and the members of a new agreement share the surplus it generates, measured against the state without that agreement. All payoff assumptions are structural. We prove that every grand state ever reached is absorbing, and that every absorbing state is grand, for every discount factor. A grand state is actually reached, almost surely, for small discount factors, for three players, and, at every discount factor, whenever distributional stakes are smaller than each player s share of the efficiency gain. Otherwise the process can fail only by cycling for ever among non-grand states. We give exact necessary conditions on such a cycle, decidable for a fixed candidate cycle by linear programming, and exhibit, under an earlier and weaker notion of profitability, a four-player payoff structure whose only closed class is a cycle of two pairs forming and dissolving alternately. Under the present definition, and under either termination rule, no equilibrium traverses a cycle on a fixed schedule: somebody always reaches a state they would rather not leave, and the axioms give them the floor. Whether arrival can fail by cycling at random is open. The axioms are not merely postulated: we exhibit a bargaining game proposal, amendment by substitutes voted on by their own signatories, final unanimity, and an arbitrarily small delay on failure whose equilibria satisfy them as the delay vanishes, and which settles each period in its first round.

Multidimensional screening is (in)famously intractable. In this paper, we study optimal screening mechanisms subject to a tractability constraint from the agent's perspective. Specifically, we require that the menu of options offered by the designer can be ordered so that, regardless of her preference type, the agent can find a utility-maximizing option via greedy search: any locally optimal choice must also be globally optimal. In one-dimensional screening with the single-crossing property, this requirement has no bite. In multidimensional environments, however, searchability restricts the set of implementable outcomes. In the multiproduct monopoly problem, the optimal searchable menu is a sparse upgrade menu: higher tiers offer higher allocation probabilities for every good, and the number of tiers is at most the number of goods. In a multidimensional screening problem with money and ordeals, the optimal searchable menu offers the agent a single way to obtain the good. In income taxation with rich multidimensional heterogeneity, a tax schedule is searchable if and only if it is progressive.

This paper develops a theoretical framework for signed optimal transport. A global flatness measure induced by the continuum transport equation serves as the regularizer. We examine transport networks from a harmonic analysis perspective, prove the existence and uniqueness of the optimal coupling in the variational problem, and provide an algorithmic scheme that guarantees lossless information transport under bi-marginal constraints. To bridge theory with practice, we design an empirical analysis framework for the resulting optimal estimators, which is sufficiently general to accommodate both time-series and panel-structural analyses of the network, owing to the intrinsic invariance properties of locally compact abelian groups.

We develop a continuous-time entry-deterrence game in which market demand evolves according to the Chan-Karolyi-Longstaff-Sanders (CKLS) stochastic differential equation, allowing mean reversion and state-dependent volatility. An incumbent with privately known strength strategically chooses advertising and promotional expenditures to influence a potential entrant's beliefs, while the entrant faces a costly, irreversible entry decision and optimally waits until market conditions justify participation. Within a dynamic Stackelberg setting, Bayesian learning, asymmetric information, stochastic demand, and strategic controls jointly determine entry and signaling behavior. Using a Feynman-type path-integral control formulation, we characterize a Markovian Nash feedback equilibrium for the firms' expenditure strategies. Our contribution is to integrate CKLS demand uncertainty, private information, irreversible entry, Bayesian belief updating, and path-integral feedback control within a unified continuous-time entry-deterrence framework, while providing a computational alternative to direct Hamilton-Jacobi-Bellman (HJB) approach. We illustrate the framework empirically using 2010-2024 revenue data for Enterprise Products Partners and Targa Resources. The resulting trajectories are qualitatively consistent with the model's predictions, exhibiting persistence, recovery after adverse shocks, and distinct responses associated with different competitive positions, while supporting the model's strategic mechanisms under uncertainty.

This article surveys emerging directions in the mathematics of democracy. It uses three case studies — voting theory, participatory budgeting, and deliberative democracy — to highlight how contemporary challenges motivate rigorous mathematical research that incorporates real-world data, institutional constraints, and implementation feasibility. Within each case, we highlight active and promising research frontiers, evidence of real-world impact, practical applications, and opportunities for getting involved.

Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves information and mechanism design. Specifically, we consider the economic setting recently introduced by Bergemann et al. (2022), where in addition to the menu of quality-price pairs, the seller offers information on the value of the match between product quality and buyer's taste via a signaling scheme. We relax the assumption that the seller knows the buyers' belief about the distribution of tastes and study the sample requirements of designing a revenue maximizing scheme. We consider both the batch setting where we have access to data from a set of i.i.d. buyers and an online demand query model where we observe the buyers' behaviors to seller's schemes. Despite the apparent non-convexity of the problem, we also give the first FPTAS to compute a scheme that maximizes the revenue within an arbitrarily small additive loss, which was left open by Bergemann et al. (2022). Overall, this brings a new learning perspective in asymmetric economic settings where buyers and sellers know different types of information.

This paper studies how robust social learning is when sampling is selective, i.e., some types of actions are more likely to be sampled by successors. We show that Bayesian agents can achieve asymptotic learning despite non-expanding observations, because the endogenous observation network itself carries information and agents have ways to undo the selection bias.

This paper develops a decision-theoretic interpretation of local expected utility on Abstract Wiener space. The framework is intended for economic acts that are naturally stochastic paths, such as income paths, consumption paths, investment payoffs, insurance losses, or laboratory stimuli unfolding over a continuum of contingencies. In this setting the object of choice is an act or payoff path, while Hermite functions serve as state-feature coordinates rather than objects of preference. Abstract Wiener space supplies a Gaussian reference measure on the Banach space of paths and a Hilbert subspace on which local utility is represented by orthogonal coefficients. The associated Wiener-integral weights are generally signed stochastic functionals; they become admissible decision weights only after a specified nonnegative normalization. This distinction clarifies the relation between the model, state-dependent utility, subjective expected utility, rank-dependent utility, and cumulative prospect theory. The main representation result gives finite primitive conditions under which projected path-valued acts admit a normalized local-utility representation. The corresponding elicitation result identifies composite utility-weight coefficients from projected acts and recovers normalized decision weights when the local utility scale is independently elicited. The paper also states testable restrictions: normalized weights must be nonnegative, add to one, preserve monotonicity, and satisfy additional rank or gain-loss restrictions when the subjective expected utility, rank-dependent utility, or cumulative prospect theory submodels are imposed. Numerical illustrations show how the representation operates in finite approximations.

In Shapley-Scarf housing markets, Ma (1994) shows that top trading cycles (TTC) is the unique mechanism satisfying individual rationality (IR), Pareto efficiency (PE), and strategy-proofness. We ask what other mechanisms become possible when strategy-proofness is replaced by a weaker condition called non-obvious manipulability (NOM), introduced by Troyan and Morrill (2020). We first show that this weaker condition does not help on its own: every IR and PE mechanism is already NOM. We therefore introduce a new condition: NOM with groups, under which each agent knows the preferences of the other members of her group, but not those of agents outside the group. This condition reduces to strategy-proofness when all agents belong to one group, and to standard NOM when every group is a singleton. Also, we introduce a participation condition called group rationality (GR), which requires that no group do worse than it would by trading only among its own members. We then define a class of mechanisms called TTC with super-groups, whose members satisfy GR, PE, and NOM with groups. The class includes mechanisms that differ from standard TTC, including mechanisms that are not strategy-proof. Furthermore, we show that every mechanism that satisfies GR, PE, and NOM with groups has the same best- and worst-case outcomes as every TTC with super-groups mechanism.