Related papers: Certifying Lemons
Recent progress towards theoretical interpretability guarantees for AI has been made with classifiers that are based on interactive proof systems. A prover selects a certificate from the datapoint and sends it to a verifier who decides the…
An expert seller chooses an experiment to influence a client's purchasing decision, but may manipulate the experiment result for personal gain. When credibility surpasses a critical threshold, the expert chooses a fully-revealing experiment…
A sender with state-independent preferences (i.e., transparent motives) privately observes a signal about the state of the world before sending a message to a receiver, who subsequently takes an action. Regardless of whether the receiver…
A seller offers an asset in a decentralised market. Buyers have private signals about their common value. I study whether the market becomes allocatively more efficient with (i) more buyers, (ii) better-informed buyers. Both increase the…
I study the optimal design of ratings to motivate agent investment in quality when transfers are unavailable. The principal designs a rating scheme that maps the agent's quality to a (possibly stochastic) score. The agent has private…
This paper studies the role of hard information in contractual and market settings in which the receiver can flexibly adjust allocations and transfers in response to the sender's disclosure. These settings include monopoly pricing,…
Randomized smoothing is the dominant standard for provable defenses against adversarial examples. Nevertheless, this method has recently been proven to suffer from important information theoretic limitations. In this paper, we argue that…
Central to privacy concerns is that firms may use consumer data to price discriminate. A common policy response is that consumers should be given control over which firms access their data and how. Since firms learn about a consumer's…
Algorithmic fairness has emerged as a central issue in ML, and it has become standard practice to adjust ML algorithms so that they will satisfy fairness requirements such as Equal Opportunity. In this paper we consider the effects of…
We propose a new notion of credibility for Bayesian persuasion problems. A disclosure policy is credible if the sender cannot profit from tampering with her messages while keeping the message distribution unchanged. We show that the…
A sender flexibly acquires evidence--which she may pay a third party to certify--to disclose to a receiver. When evidence acquisition is overt, the receiver observes the evidence gathering process irrespective of whether its outcome is…
A multiproduct seller is more informed than consumers about the value of her products to consumers. The seller posts a price list and segments the market through cheap-talk communication. We find that when both seller's and consumers'…
We revisit the classic job-market signaling model of \cite{spence1973job}, introducing profit-seeking schools as intermediaries that design the mapping from candidates' efforts to job-market signals. Each school commits to an attendance fee…
This paper studies a game in which an informed sender with state-independent preferences uses verifiable messages to convince a receiver to choose an action from a finite set. We characterize the equilibrium outcomes of the game and compare…
I study how organisations choose selection procedures in a competitive environment. Two firms compete to hire candidates of unknown productivity from a common pool. Firms simultaneously post a selection procedure which consists of a test…
We study the power of price discrimination via an intermediary in bilateral trade, when there is a revenue-maximizing seller selling an item to a buyer with a private value drawn from a prior. Between the seller and the buyer, there is an…
We study an information design problem with two informed senders and a receiver in which, in contrast to traditional Bayesian persuasion settings, senders do not have commitment power. In our setting, a trusted mediator/platform gathers…
In this paper, we study learning in probabilistic domains where the learner may receive incorrect labels but can improve the reliability of labels by repeatedly sampling them. In such a setting, one faces the problem of whether the fixed…
Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…
We study misspecified Bayesian learning in principal-agent relationships, where an agent is assessed by an evaluator and rewarded by the market. The agent's outcome depends on their innate ability, costly effort -- whose effectiveness is…