betaFeedback

WorksEconomics, Econometrics and Finance

Learning to Design Information

Abstract

Information designers, such as large language models and online platforms, often do not know the subjective beliefs of their receivers or users. We construct learning algorithms enabling the designer to learn the belief of a strategic receiver through repeated interactions. Our learning algorithms are robust to the receiver's strategic manipulation of the learning process of the designer. We study regret relative to two benchmarks to measure the performance of the algorithms. The static benchmark is TT times the single-period optimum for the designer under a known belief. The dynamic benchmark, which is stronger, characterizes global dynamic optimality for the designer under a known belief. Our learning algorithms allow the designer to achieve no regret against both benchmarks at fast convergence speeds of O(log⁡2TT)O(\frac{\log^2 T}{T}), significantly faster than other approaches in the literature.

Latest version available here.

†Department of Economics, Boston University, email: [email protected]

‡Microsoft Research, New England and the School of Engineering and Applied Sciences, Harvard University, email: [email protected]

Introduction

An information designer (the designer; she) sends signals about an unknown state to steer the action of a receiver (he) in her favor. Designing the optimal signaling strategy requires the designer to know the receiver’s prior belief over states. Canonical economic models [e.g. 21] assume the parties share a common prior. In many applications, however, the designer has limited knowledge of the receiver’s belief. We study how she can learn that belief through repeated interactions and design approximately optimal signaling strategies when the receiver acts strategically.

For example, consider a large language model (LLM) API platform (the designer) that provides a business user (the receiver) with access to LLMs through Application Programming Interfaces (APIs). The LLM API platform charges the user based on the amount of tokens consumed to handle the user’s request. After the user submits a request, the platform has an internal evaluation about how likely the request will be successfully handled, for example, high confidence and low confidence (the state). Based on that internal assessment of the success probability, the platform then decides how to signal to the user, e.g., recommending the user to proceed for more details or admitting its inability to provide a reliable solution. Upon receiving the signal, the user updates his belief about the success probability of his request, and then takes an action to maximize his payoff, such as obeying the platform’s recommendation to proceed or stopping the interaction. The platform always prefers that the user proceed to gain payment from the user for the token consumption, regardless of the state. On the user’s side, his payoff is the highest when he pays for tokens that truly solve his request and the lowest when he pays for tokens that generate unwanted content, such as hallucinations.

The user has a subjective prior belief about the states, but the platform may not know that belief. As a result, the limited knowledge of the user’s belief fundamentally constrains the platform from designing the optimal signaling scheme. As implied by our previous work (Li and Lin, 2025), the platform may learn the user’s belief in the case where the user’s belief equals the true distribution through the user’s actions. However, the user may choose deceptive actions in some periods on purpose to manipulate the platform’s learning of his prior belief and further the platform’s design of the signaling scheme in favor of the user himself.

Motivated by such scenarios, we study an information design problem where the subjective prior belief of the receiver is unknown to the designer and the receiver is strategic.

Standard economic models, when tackling the problem of an unknown belief, would assume that the designer has a distribution over possible prior beliefs of the receiver [e.g. 1, 22]. However, such an approach suffers from several concerns, such as computational hardness. A detailed discussion of the drawbacks of such an approach is presented in the literature review in detail.

Are there near-optimal signaling strategies for the designer when she does not know the subjective prior belief of a strategic receiver? Our main contribution is to construct approximately optimal signaling schemes which enable the designer to learn that subjective prior from repeated interactions with a strategic receiver. Moreover, our designer achieves such approximate optimality at efficient speeds. In addition, the designer’s learning is robust to the receiver’s strategic manipulation. Finally, such fast learning speeds are achieved against both a static benchmark and a dynamic benchmark.

Specifically, we study a learning model where an information designer (e.g., the LLM platform) learns to design signaling schemes over TT periods based on historical interactions with a long-lived receiver (e.g., a business user). The designer does not know the belief of the receiver. In each period, the designer chooses a signaling scheme, which maps a state i.i.d. sampled from a true distribution over the states to a randomized signal. Upon receiving the signal, the receiver updates his belief about the state and takes an action. The payoffs of the two players are then realized. We design learning algorithms for the designer to improve the signaling schemes over time, such that (1) the designer’s time-averaged payoff converges to optimum benchmarks and that (2) the convergence is fast, while (3) being robust to strategic manipulation by the receiver.

The rate at which the designer’s payoff converges to the optimal objective depends on the learning algorithm she employs. We measure the performance of the learning algorithm by a general notion of regret: the difference between the designer’s time-cumulative actual payoffs and an optimality benchmark, based on what the designer could achieve if she knew the receiver’s belief. We first characterize different regret benchmarks for the problem of an unknown prior belief in a learning model. The static benchmark is TT times the single-period optimum for the designer had the designer known the receiver’s belief. The static regret is defined relative to the static benchmark. This allows us to relate our results to the results of the canonical information design models in Kamenica and Gentzkow [21].

In addition, we consider a dynamic benchmark that measures the designer’s global dynamic optimality under a known belief, which is stronger than the static benchmark. The dynamic regret is then defined relative to the dynamic benchmark. A learning algorithm is called no-regret if its regret grows sublinearly with time (alternatively, its time-averaged regret converges to zero). The rate at which the time-averaged regret declines reflects the learning algorithm’s efficiency. We aim to design learning algorithms that not only achieve no regret against the two benchmarks, but also yield fast convergence to optimality under the unknown belief while being robust to the receiver’s strategic manipulation.

Our first main result is an O(log⁡2T)O(\log^{2} T) upper bound on the static regret. Our second main result is also an O(log⁡2T)O(\log^{2} T) regret upper bound on the dynamic regret. We design two learning algorithms to ensure that, for any problem instance, the designer’s regrets for TT periods, relative to the static benchmark and the dynamic benchmark, respectively, are both no more than a constant times log⁡2T\log^2 T for all TT. Both regret upper bounds imply convergence rates of O(log⁡2TT)O\left(\frac{\log^2 T}{T}\right) for the designer’s regret to converge to zero, which are significantly faster than other approaches in the literature, as discussed later.

Both of our two learning algorithms contain two phases. The first phase is the learning of the receiver’s belief, which has the same learning logic under the two regret benchmarks. The learning of the belief is based on binary search. The key idea is to learn the unknown belief from the receivers’ actions. To see the intuition, consider two states and two actions, where the receiver prefers different actions in the two states. For the moment, suppose the receiver is myopic in the sense that he does not consider the future in choosing his action. Then, the designer can compute a cutoff belief such that the receiver is indifferent between the two actions. The actual action chosen by the receiver then reveals whether the receiver’s belief is below or above the cutoff. By observing the receiver’s action, the designer gradually narrows down the range of possible values for the prior. That process does not stop until the designer obtains a sufficiently accurate estimate of the prior belief. Our formal analysis shows how to generalize that intuition to multiple states and multiple actions.

How can the designer learn the receiver’s belief when the receiver is not myopic? The algorithm limits the strategic manipulation from the receiver by delaying the effect of the receiver’s action on future signaling schemes. In particular, in each iteration, the algorithm records the receiver’s action when the designated signal first occurs. It then waits a fixed number of additional periods before using that recorded action to update the signaling scheme, ignoring actions taken during the waiting periods. Thus, the recorded action can influence future information only after a delay. Since the receiver discounts future payoffs, a sufficiently long delay makes the potential gain from manipulation small relative to any substantial immediate payoff loss. The receiver may still deviate from a myopic best response when the immediate loss is small, but the resulting error in the belief estimate is small. By choosing the delay appropriately, the designer can therefore learn the receiver’s belief to the desired accuracy despite the receiver’s strategic manipulation.

The second phase, where our learning algorithms for the two benchmarks differ, is robustification. The signaling scheme that is optimal for the designer under the belief estimate is converted into another signaling scheme that is approximately optimal under the receiver’s belief. The motivation is that even if two prior beliefs are very close, the signaling scheme optimal under one belief may perform arbitrarily badly under the other, leaving no guarantee on the designer’s payoff. However, the robustification varies across benchmarks. Our first learning algorithm uses static robustification, where the robustification process is performed on the signaling scheme optimal for the belief estimate once to obtain a robustified signaling scheme for being repeatedly used for future periods.

Our second learning algorithm applies a dynamic robustification to the designer’s globally optimal strategy, where the signaling schemes in different periods are chosen so that the receiver at any period is still incentivized to participate in the future. The challenge is that the static robustification may backfire: the static robustification only increases the persuasiveness of the signaling scheme, namely, increasing the positive gap of the expected payoff from the recommended action relative to that from any other actions. However, the static robustification may lower the receiver’s ex ante (before a recommendation is sent) expected payoff from obeying the recommendations in the future. Thus, after an action is recommended by a statically robustified signaling scheme, the receiver’s incentive to obey that current recommendation becomes stronger, but his ex ante payoff from obeying recommendations in future periods may get worse, potentially violating the receiver’s participation constraint.

To overcome this, we propose payoff-improving robustification, which weakly increases the receiver’s ex ante payoff from being obedient. We then take the designer’s optimal dynamic signaling strategy, given her belief estimate, and apply the payoff-improving robustification procedure to each period’s signaling scheme in that dynamic strategy. We show that the resulting dynamic strategy is persuasive for the receiver and approximately optimal for the designer.

The efficacy of both of our learning algorithms is reflected by the logarithmic upper bounds on their regrets: O(log⁡2T)O(\log^{2} T). That means that the designer’s average payoff converges to the optimality benchmarks at a fast speed, in the order of O(log⁡2TT)O\left(\frac{\log^{2} T}{T}\right). In contrast, an intuitive method is to use an empirical estimation: using the empirical frequency to estimate the state distribution. Empirical estimation does not work in our problem as the receiver’s belief is subjective and may not equal the true distribution over states. Even if empirical estimation could be applied, it would suffer a regret of at least O(T)O(\sqrt{T}) due to sampling error, which is exponentially worse than the O(log⁡2T)O(\log^{2} T) regret bound of our learning algorithms. Our algorithms circumvent the limitation of empirical estimation and achieve an exponential improvement by actively learning the receiver’s belief from his actions.

Related Work

First, this paper contributes to the literature on robust information design under uncertainty, especially when the designer lacks knowledge of the receiver’s prior belief. Classical models such as Bayesian persuasion [21, 5] and cheap talk [10] typically assume a common prior shared by the designer and the receiver. Different from the canonical models, Alonso and Câmara [1] study persuasion with heterogeneous priors. Recent work relaxes this by introducing uncertainty over the prior. One approach assumes the designer holds a belief over the unknown prior (e.g., Alonso and Câmara [1]), but computing the optimal signaling scheme is generally intractable [19]. Another approach, rooted in robust mechanism design, has the designer optimize against a worst-case prior in a set of possible priors. Kosterina [23] studies a designer who chooses a signaling scheme to maximize her payoff under the least favorable receiver prior in a given set. Hu and Weng (2021) and Dworczak and Pavan [11] consider uncertainty about the receiver’s private information or additional information sources. These papers typically study a single-shot game, limiting the designer’s ability to learn over time. Of course, when the designer has the opportunity to learn, one expects she may achieve a much higher payoff. In contrast, we design learning algorithms that infer the prior, achieving near optimality quickly while avoiding computational hardness.

Departing from the standard approach for addressing the robustness, Li and Lin (2025) study how to learn the belief of a sequence of short-lived receivers from their actions. However, if a receiver interacts with the platform repeatedly, thus becoming long-lived, then he will be incentivized to be strategic. Thus, he may take actions to convey deceptive information about his belief, manipulating the platform’s learning in a direction favorable to them but unfavorable to the platform.

Our work also relates to dynamic information provision. Ball [4] consider a dynamic information design problem in which the beliefs of the designer and the receiver are different. However, their model uses persistent states while we consider i.i.d. states. More importantly, they consider both players to be equally patient, while we consider a patient designer and an impatient receiver. The different patience levels in our paper have crucial influence on their dynamic strategies and the designer’s regret benchmarks. Besides, they assume more structure on the dynamic process and the players’ payoffs, while our work keep the dynamic process and the payoff functions general without further structure.

Our work also contributes to the literature on online Bayesian persuasion, which studies learning when some game parameters are unknown. Castiglioni et al. [8], Castiglioni et al. [9], and Feng, Tang, and Xu [13] consider unknown receiver utilities; Zu, Iyer, and Xu (2021) and Wu et al. (2022) focus on unknown priors; and Bacchiocchi et al. [3] allow both utilities and priors to be unknown. Previous approaches to unknown priors rely on empirical estimation and incur Ω(T)\Omega(\sqrt{T}) regret due to sampling error. This option is not available here as the designer needs to learn the receiver’s belief, not the true distribution. We bypass this by using best responses to infer the prior more efficiently, achieving O(log⁡2T)O(\log^{2} T) regret. Camara, Hartline, and Johnsen [7] also study information design with learning agents but drop distributional assumptions and allow adversarial state sequences; their regret notion therefore differs from ours, which assumes i.i.d. states from an unknown objective prior.

Our work also connects to the line of works on misspecified learning (Ba, 2023; [6]; [14]; [12]; Fudenberg, Lanzani, and Strack, 2021; Fudenberg, Romanyuk, and Strack, 2017) and on the long-run outcomes of misspecified Bayesian agents who cannot obtain the true distribution over states (e.g., [27, 26, 15] (), and He and Libgober 2021)). Those works study belief convergence and actions in general learning environments. One can view our model as studying a receiver whose belief is the limiting outcome of his misspecified learning. We do not analyze the process by which this belief is formed, focusing instead on how the designer interacts with a receiver whose belief has already converged.

Models and Prelimaries

Models

Single-period game. We first define a single-period game of information design (Bayesian persuasion) with subjective prior beliefs. There is a finite set of states of the world Ω\Omega. The information designer and the receiver have subjective prior beliefs μD,μR∈Δ(Ω)\mu_D, \mu_R \in\Delta(\Omega) over the states, respectively, where Δ(Ω)\Delta(\Omega) denotes the set of probability distributions over Ω\Omega. We think of μD\mu_D as the true distribution over the states and μR\mu_R as a subjective prior belief over the states, which may not be the same as the true distribution. The designer is better informed about the true distribution from access to sufficient state observation data, so the designer is assumed to know the true distribution. The receiver’s prior μR\mu_R can be different from the true distribution, which may be the convergence outcome of the learning process of a misspecified belief (e.g., [17]).

The receiver has a finite set of actions AA. The designer and the receiver have payoff functions u,v:A×Ω→[0,1]u, v : A \times\Omega\to[0,1], respectively. This single-period game is summarized by an instance I=(Ω,A,u,v,μD,μR)\mathcal{I} = (\Omega, A, u, v, \mu_D, \mu_R).

At the beginning of the game, the designer announces a signaling scheme π:Ω→Δ(S)\pi: \Omega\to\Delta(S), which maps each state to a probability distribution over a finite set of signals SS. Let Π=Ω→Δ(S)\Pi= \Omega\to\Delta(S) be the set of signaling schemes. The receiver believes that the state is drawn according to the distribution μR\mu_R. Thus, after receiving a signal s∼π(⋅∣ω)s \sim\pi(\cdot|\omega) sampled according to state ω\omega and the signaling scheme π\pi, the receiver obtains his posterior belief μR(ω)π(s∣ω)∑ω′∈ΩμR(ω′)π(s∣ω′)\frac{\mu_R(\omega)\pi(s|\omega)}{\sum_{\omega'\in\Omega}\mu_R(\omega')\pi(s|\omega')}, ∀ω∈Ω\forall\omega\in\Omega, and takes an action in response. Let ρ:S→Δ(A)\rho: S \to\Delta(A) be a possibly randomized single-period strategy of the receiver. Under a pair of strategies (π,ρ)(\pi,\rho), the expected payoffs of the designer and the receiver in in the single-period game are, respectively,

U(π,ρ;μD)=∑ω∈ΩμD(ω)∑s∈Sπ(s∣ω)∑a∈Aρ(a∣s)u(a,ω).(1)U(\pi,\rho;\mu_D)=\sum_{\omega\in\Omega}\mu_D(\omega)\sum_{s\in S}\pi(s\mid\omega)\sum_{a\in A}\rho(a\mid s)u(a,\omega). \tag*{(1)}
V(π,ρ;μR)=∑ω∈ΩμR(ω)∑s∈Sπ(s∣ω)∑a∈Aρ(a∣s)v(a,ω).(2)V(\pi,\rho;\mu_R)=\sum_{\omega\in\Omega}\mu_R(\omega)\sum_{s\in S}\pi(s\mid\omega)\sum_{a\in A}\rho(a\mid s)v(a,\omega). \tag*{(2)}

We say the receiver myopically best responds2 if he maximizes his single-period payoff by choosing a strategy

ρ∗∈arg⁡max⁡ρ:S→Δ(A) V(π,ρ)\rho^* \in\underset{\rho:S\to\Delta(A)}{\arg\max}\ V(\pi,\rho)

or, equivalently, an action ρ∗(s)∈arg⁡max⁡a∈AμR(ω)π(s∣ω)v(a,ω)\rho^*(s)\in\arg\max_{a\in A}\mu_R(\omega)\pi(s\mid\omega)v(a,\omega) given each signal s∈Ss\in S based on his posterior belief. With a myopically best-responding receiver, the optimal utility of the designer is

UBP∗(I):=max⁡π∈Π max⁡ρ∈arg⁡max⁡s→Δ(A)V(π,ρ;μR)U(π,ρ;μD).(3)U^*_{\mathrm{BP}}(\mathcal{I}) := \max_{\pi\in\Pi}\ \max_{\rho\in\arg\max_{s\to\Delta(A)} V(\pi,\rho;\mu_R)} U(\pi,\rho;\mu_D). \tag*{(3)}

We call UBP∗(I)U^*_{\mathrm{BP}}(\mathcal{I}) the Bayesian persuasion benchmark.

TT-period learning process. We consider the TT-period repetitions of the above single-period game with an instance I=(Ω,A,u,v,μD,μR)\mathcal{I}=(\Omega,A,u,v,\mu_D,\mu_R). Importantly, the designer now does not know the receiver’s prior belief μR\mu_R but she knows other parameters u,v,μDu,v,\mu_D. In particular, the designer learns to design signaling schemes using an algorithm G\mathcal{G} which, at every period tt, maps the history H(t−1)∈Π(t−1)×S(t−1)×A(t−1)H^{(t-1)}\in\Pi^{(t-1)}\times S^{(t-1)}\times A^{(t-1)} to a signaling scheme π(t)∈Π\pi^{(t)}\in\Pi for the current period. In response to the learning algorithm G\mathcal{G}, the receiver chooses a TT-period strategy ϕ=(ϕ(t))t=1T\phi=(\phi^{(t)})_{t=1}^{T} where each ϕ(t)\phi^{(t)} maps the history H(t−1)∈Π(t−1)×S(t−1)×A(t−1)H^{(t-1)}\in\Pi^{(t-1)}\times S^{(t-1)}\times A^{(t-1)} and the current period’s signaling scheme π(t)∈Π\pi^{(t)}\in\Pi to a strategy ρ(t):S→Δ(A)\rho^{(t)}:S\to\Delta(A) that specifies a randomized action for each possible signal. Then, the pair of strategies (G,ϕ)(\mathcal{G},\phi) will generate a stochastic sequence of (π(t),ρ(t))t=1T(\pi^{(t)},\rho^{(t)})_{t=1}^{T} of the designer’s signaling schemes and the receiver’s single-period strategies. We assume that the receiver is impatient in the sense that he has a discount factor γ∈(0,1)\gamma\in(0,1), so his total discounted expected payoff is

VT(G,ϕ;μR)=E(π(t),ρ(t))t=1T∼(G,ϕ)[∑t=1Tγt⋅V(π(t),ρ(t);μR)].(4)V_T(\mathcal{G},\phi;\mu_R)=\mathbb{E}_{(\pi^{(t)},\rho^{(t)})_{t=1}^{T}\sim(\mathcal{G},\phi)}\left[\sum_{t=1}^{T}\gamma^t\cdot V(\pi^{(t)},\rho^{(t)};\mu_R)\right]. \tag*{(4)}

The designer, on the other hand, is patient, that is, having a discount factor of one. The designer aims to maximize her total expected payoff

UT(G,ϕ;μD)=E(π(t),ρ(t))t=1T∼(G,ϕ)[∑t=1TU(π(t),ρ(t);μD)].(5)U_T(\mathcal{G}, \phi; \mu_D) = \mathbb{E}_{(\pi^{(t)},\rho^{(t)})_{t=1}^{T}\sim(\mathcal{G},\phi)}\left[\sum_{t=1}^{T} U(\pi^{(t)},\rho^{(t)};\mu_D)\right]. \tag*{(5)}

We consider a strategic (or long-lived) receiver who best responds to the designer’s learning algorithm G\mathcal{G}. Formally, given the algorithm G\mathcal{G} and the belief μR\mu_R, the receiver chooses a globally optimal strategy

ϕ∗(G,μR)=arg⁡max⁡ϕ VT(G,ϕ;μR).\phi^*(\mathcal{G},\mu_R) = \underset{\phi}{\arg\max}\ V_T(\mathcal{G},\phi;\mu_R).

Then, the designer obtains her total expected payoff

References

  1. [1]Alonso, Ricardo and Odilon Câmara (Sept. 2016). “Bayesian persuasion with heterogeneous priors”. en. In: Journal of Economic Theory 165, pp. 672–706. ISSN: 00220531. DOI: 10.1016/j.jet.2016.07.006. URL: https://linkinghub.elsevier.com/retrieve/pii/S0022053116300497 (visited on 12/22/2023).DOI
  2. [3]Bacchiocchi, Francesco et al. (2024). Markov Persuasion Processes: Learning to Persuade from Scratch. URL: https://arxiv.org/abs/2402.03077.
  3. [4]Ball, Ian (2023). “Dynamic Information Provision: Rewarding the Past and Guiding the Future”. In: Econometrica 91.4, pp. 1363–1391. DOI: https://doi.org/10.3982/ECTA17345. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.3982/ECTA17345. URL: https://onlinelibrary.wiley.com/doi/abs/10.3982/ECTA17345.
  4. [5]Bergemann, Dirk and Stephen Morris (May 2016). “Information Design, Bayesian Persuasion, and Bayes Correlated Equilibrium”. In: American Economic Review 106.5, pp. 586–91. DOI: 10.1257/aer.p20161046. URL: https://www.aeaweb.org/articles?id=10.1257/aer.p20161046.DOI
  5. [6]Bohren, J. Aislin and Daniel N. Hauser (2021). “LEARNING WITH HETEROGENEOUS MISSPECIFIED MODELS: CHARACTERIZATION AND ROBUSTNESS”. In: Econometrica 89.6, pp. 3025–3077. ISSN: 00129682, 14680262. URL: https://www.jstor.org/stable/48636220 (visited on 09/26/2025).
  6. [7]Camara, Modibo K., Jason D. Hartline, and Aleck C. Johnsen (2020). “Mechanisms for a No-Regret Agent: Beyond the Common Prior”. In: 2020 IEEE 61st Annual Symposium on Foundations of Computer Science (FOCS), pp. 259–270. URL: https://api.semanticscholar.org/CorpusID:221640554.arxiv.org/abs/2009.05518
  7. [8]Castiglioni, Matteo et al. (2020). “Online Bayesian Persuasion”. In: Advances in Neural Information Processing Systems. Vol. 33. Curran Associates, Inc., pp. 16188–16198. URL: https://proceedings.neurips.cc/paper/2020/file/ba5451d3c91a0f982f103cdbe249bc78-Paper.pdf.
  8. [9]Castiglioni, Matteo et al. (July 2021). “Multi-Receiver Online Bayesian Persuasion”. In: Proceedings of the 38th International Conference on Machine Learning. Vol. 139. Proceedings of Machine Learning Research. PMLR, pp. 1314–1323. URL: https://proceedings.mlr.press/v139/castiglioni21a.html.arxiv.org/abs/2106.06480
  9. [10]Crawford, Vincent P. and Joel Sobel (Nov. 1982). “Strategic Information Transmission”. In: Econometrica 50.6, p. 1431. ISSN: 00129682. DOI: 10.2307/1913390. URL: https://www.jstor.org/stable/1913390?origin=crossref (visited on 11/21/2023).DOI
  10. [11]Dworczak, Piotr and Alessandro Pavan (2022). “Preparing for the Worst but Hoping for the Best: Robust (Bayesian) Persuasion”. In: Econometrica 90.5, pp. 2017–2051. DOI: https://doi.org/10.3982/ECTA19107. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.3982/ECTA19107. URL: https://onlinelibrary.wiley.com/doi/abs/10.3982/ECTA19107.
  11. [12]Esponda, Ignacio, Demian Pouzo, and Yuichi Yamamoto (2021). “Asymptotic behavior of Bayesian learners with misspecified models”. In: Journal of Economic Theory 195, p. 105260. ISSN: 0022-0531. DOI: https://doi.org/10.1016/j.jet.2021.105260. URL: https://www.sciencedirect.com/science/article/pii/S0022053121000776.
  12. [13]Feng, Yiding, Wei Tang, and Haifeng Xu (July 2022). “Online Bayesian Recommendation with No Regret”. en. In: Proceedings of the 23rd ACM Conference on Economics and Computation. Boulder CO USA: ACM, pp. 818–819. ISBN: 978-1-4503-9150-4. DOI: 10.1145/3490486.3538327. URL: https://dl.acm.org/doi/10.1145/3490486.3538327 (visited on 10/17/2022).DOI
  13. [14]Frick, Mira, Ryota Iijima, and Yuhta Ishii (None 2023). “Belief Convergence under Misspecified Learning: A Martingale Approach”. In: The Review of Economic Studies 90.2, pp. 781–814. DOI: None. URL: https://ideas.repec.org/a/oup/restud/v90y2023i2p781-814..html.DOI
  14. [15]Fudenberg, Drew and Giacomo Lanzani (2023). “Which misspecifications persist?” In: Theoretical Economics 18.3, pp. 1271–1315. DOI: https://doi.org/10.3982/TE5298. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.3982/TE5298. URL: https://onlinelibrary.wiley.com/doi/abs/10.3982/TE5298.
  15. [17]Fudenberg, Drew, Gleb Romanyuk, and Philipp Strack (Sept. 2017). “Active learning with a misspecified prior”. In: Theoretical Economics 12.3, None. DOI: None. URL: https://ideas.repec.org/a/the/publsh/2480.html.
  16. [19]Hossain, Safwan et al. (July 2024). “Multi-Sender Persuasion: A Computational Perspective”. In: Proceedings of the 41st International Conference on Machine Learning. Vol. 235. Proceedings of Machine Learning Research. PMLR, pp. 18944–18971. URL: https://proceedings.mlr.press/v235/hossain24c.html.arxiv.org/abs/2402.04971
  17. [21]Kamenica, Emir and Matthew Gentzkow (Oct. 2011). “Bayesian Persuasion”. en. In: American Economic Review 101.6, pp. 2590–2615. ISSN: 0002-8282. DOI: 10.1257/aer.101.6.2590. URL: https://pubs.aeaweb.org/doi/10.1257/aer.101.6.2590 (visited on 10/22/2022).DOI
  18. [22]Kolotilin, Anton et al. (2017). “Persuasion of a Privately Informed Receiver”. en. In: Econometrica 85.6, pp. 1949–1964. ISSN: 0012-9682. DOI: 10.3982/ECTA13251. URL: https://www.econometricsociety.org/doi/10.3982/ECTA13251 (visited on 12/22/2023).DOI
  19. [23]Kosterina, Svetlana (July 2022). “Persuasion with unknown beliefs”. In: Theoretical Economics 17.3, None. DOI: None. URL: https://ideas.repec.org/a/the/publsh/4742.html.DOI
  20. [25]Myerson, Roger B. (1986). “Multistage Games with Communication”. In: Econometrica 54.2, pp. 323–358. ISSN: 00129682, 14680262. URL: http://www.jstor.org/stable/1913154 (visited on 07/01/2025).DOI
  21. [26]Rabin, Matthew and Joel L. Schrag (1999). “First Impressions Matter: A Model of Confirmatory Bias”. In: The Quarterly Journal of Economics 114.1, pp. 37–82. ISSN: 00335533, 15314650. URL: http://www.jstor.org/stable/2586947 (visited on 09/27/2025).DOI
  22. [27]Tversky, Amos and Daniel Kahneman (1973). “Availability: A heuristic for judging frequency and probability”. In: Cognitive Psychology 5.2, pp. 207–232. ISSN: 0010-0285. DOI: https://doi.org/10.1016/0010-0285(73)90033-9. URL: https://www.sciencedirect.com/science/article/pii/0010028573900339.

Paper details

vlnc:W_d4rd4wvx
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Economics, Econometrics and Finance

Not recorded for this paper

View statement
Looking for related papers…
Contents